ABSTRACT
Abstract
A method of configuring a robot of a fleet of robots for use of an AI chipset includes receiving a request for a robotic fleet to perform a job. The method includes defining a set of tasks that are to be performed by the robotic fleet in performance of the job. The method includes assigning at least one task of the set of tasks to a robot. The method includes determining a configuration for the robot based on the assigned task and a components inventory that indicates different components that can be provisioned to the robot including at least one AI chipset, and for each component, a set of extended capabilities and a status of the component. The method includes configuring the robot based on the determined configuration to use the at least one AI chipset. The method includes deploying the robotic fleet to perform the job.
Description
CROSS-REFERENCE TO RELATED APPLICATIONS
This application is a continuation of PCT/US2021/064233 filed Dec. 17, 2021, which claims the benefit of U.S. Provisional App. No. 63/127,983 filed Dec. 18, 2020 and U.S. Provisional App. No. 63/185,348 filed May 6, 2021 and claims priority to India App. No. IN202111029964 filed Jul. 3, 2021 and India App. No. IN202111036187 filed Aug. 10, 2021. The entire disclosures of the above applications are incorporated by reference.
FIELD
The present disclosure relates to information technology methods and systems for management of value chain network entities, including supply chain and demand management entities. The present disclosure also relates to the field of enterprise management platforms, more particularly involving data management, artificial intelligence, network connectivity and digital twins, additive manufacturing, robotics-as-a-service, and energy management.
BACKGROUND
Historically, many of the various categories of goods purchased and used by household consumers, by businesses and by other customers were supplied mainly through a relatively linear fashion, in which manufacturers and other suppliers of finished goods, components, and other items handed off items to shipping companies, freight forwarders and the like, who delivered them to warehouses for temporary storage, to retailers, where customers purchased them, or directly to customer locations. Manufacturers and retailers undertook various sales and marketing activities to encourage and meet demand by customers, including designing products, positioning them on shelves and in advertising, setting prices, and the like.
Orders for products were fulfilled by manufacturers through a supply chain, such as depicted in FIG. 1 , where suppliers 122 in various supply environments 160 , operating production facilities 134 or acting as resellers or distributors for others, made a product 130 available at a point of origin 102 in response to an order. The product 130 was passed through the supply chain, being conveyed and stored via various hauling facilities 138 and distribution facilities 134 , such as warehouses 132 , fulfillment centers 112 and delivery systems 114 , such as trucks and other vehicles, trains, and the like. In many cases, maritime facilities and infrastructure, such as ships, barges, docks and ports provided transport over waterways between the points of origin 102 and one or more destinations 104 .
Organizations have access to an almost unlimited amount of data. With the advent of smart connected devices, wearable technologies, the Internet of Things (IoT), and the like, the amount of data available to an organization that is planning, overseeing, managing and operating a value chain network has increased dramatically and will likely to continue to do so. For example, in a manufacturing facility, warehouse, campus, or other operating environment, there may be hundreds to thousands of IoT sensors that provide metrics such as vibration data that measure the vibration signatures of important machinery, temperatures throughout the facility, motion sensors that can track throughput, asset tracking sensors and beacons to locate items, cameras and optical sensors, chemical and biological sensors, and many others. Additionally, as wearable technologies become more prevalent, wearables may provide insight into the movement, health indicators, physiological states, activity states, movements, and other characteristics of workers. Furthermore, as organizations implement CRM systems, ERP systems, operations systems, information technology systems, advanced analytics and other systems that leverage information and information technology, organizations have access to an increasingly wide array of other large data sets, such as marketing data, sales data, operational data, information technology data, performance data, customer data, financial data, market data, pricing data, supply chain data, and the like, including data sets generated by or for the organization and third-party data sets.
The presence of more data and data of new types offers many opportunities for organizations to achieve competitive advantages; however, it also presents problems, such as of complexity and volume, such that users can be overwhelmed, missing opportunities for insight. A need exists for methods and systems that allow enterprises not only to obtain data, but to convert the data into insights and to translate the insights into well-informed decisions and timely execution of efficient operations.
Additive Manufacturing
Additive manufacturing, encompassing technologies like 3D printing, vapor deposition, polymer (or other material) coating, epitaxial and/or crystalline growth approaches, and others, alone or in combination with other technologies, such as subtractive or assembly technologies, enables manufacturing of a three-dimensional product from a design via a process of forming successive layers of the product, with optional interim or subsequent steps to arrive at a finished component or system. The design may be in the form of a data source like an electronic 3D model created with a computer aided design package or via 3D scanner. The 3D printing or other additive process then involves forming a first material-layer and then adding successive material layers wherein each new material-layer is added on a pre-formed material-layer, until the entire designed three-dimensional product is completed. References to 3D printing or other particular additive manufacturing technologies throughout this disclosure should be understood to encompass alternative embodiments involving other additive manufacturing technologies, except where context specifically indicates otherwise.
A large number of additive processes are currently available. They may differ in the manner successive layers are deposited to create the 3D product. They may also differ in terms of materials that are used to form the product. Metals (such term including alloys except where context specifically indicates otherwise and including specialized metals such as shape memory materials) are increasingly popular 3D printing materials. Common ones include Titanium, Stainless steel, Aluminum, Tool Steel, Inconel and Cobalt Chrome. Some methods melt or soften metal to produce the layers. Examples of metal 3D printing methods include selective laser melting (SLM), selective laser sintering (SLS), direct metal laser sintering (DMLS) and/or fused deposition modeling (FDM). Other methods include: (a) metal extrusion where a filament or rod consisting of polymer and heavily loaded with metal powder is extruded through a nozzle (like in FDM) to form the âgreenâ part that is post-processed (debinded and sintered) to create a fully-metal part; (b) metal binder jetting that uses print-heads to apply a liquid binding agent onto layers of powder and (c) nanoparticle jetting that uses jetting of metal nanoparticles from inkjet nozzles in super-thin layers.
Regardless of the design data sources or the methods employed for additive manufacturing, including metal 3D printing, the entire process from design and manufacturing to end customer delivery, remains prone to inefficiency, process variations, product inconsistency, and unreliability. This can result in a final 3D printed product that does not meet customer expectations and/or product specifications, and it can lead to low quality 3D printed products or components that result in failures, among other problems. These issues can also increase operating costs for 3D printing service providers through material waste, reduced throughput due to machine downtime and/or unproductive print hours, and associated supply chain risks and inefficiencies. For example, it is common for 3D printed products to get deformed during or after the manufacture due to printing procedures and non-optimized printing parameters. Also, common issues that can arise due to inefficient manufacturing supply chains include fraud, delayed deliveries, contractual liability, and product recalls.
To ensure that the final metal 3D printed product matches the customer expectations and producer specifications around quality, cost and turnaround time, a need exists for smarter product design, manufacturing, supply chain and demand management methods and systems. A further need exists for methods and systems that allow for improved monitoring, management, and optimization of additive manufacturing capabilities by and for various interested parties.
Conventional machine vision systems are made of a combination of optics, lighting, sensors and software and aim to replicate the function of human eye. Such systems create an image of an object by capturing and analyzing the reflected light from the object. An optical lens captures the image and presents it to an image sensor such as a charge coupled device (CCD) or complementary metal oxide semiconductor (CMOS) device. Such devices contain matrices or linear arrays of small, accurately spaced photo sensitive elements fabricated on silicon chips using integrated circuit technology. The sensor device converts the light falling on it, through the camera lens, into analog electrical signal corresponding to light intensity. The object image is thus broken down into an array of individual picture elements or pixels. An analog to digital converter is used to convert analog voltage of element into digital value. If voltage level for each pixel is given either 0 or 1 value depending on some threshold value, it is called binary system. On the other hand, a gray scale system assigns up to 256 different values depending on intensity to each pixel. Thus, in addition to black and white, many different shades of gray can be distinguished. A gray-scale image may be seen to have one channel, represented by a 2-D matrix of pixels having pixel values in the range of, for example, 0 to 255. A color image on the other hand represents the brightness and color of the pixels in an image by the three primary color values: R (red), G (green), and B (blue). Thus, color images have red, green, and blue (RGB) channels each representing RGB components of the image. This raw data captured by the image sensor is then sent to an image processing system for analysis. The image processing system then processes the raw data to extract useful information to analyze the image and make decisions on such analysis. The image processing system may include a pre-processing function to enhance the image quality. For example, such processing may involve image scaling, noise reduction, color adjustment, brightness adjustment, white balance adjustment, sharpness, adjustment, contrast adjustment and the like. Further the image may be analyzed using machine learning or other algorithms to identify one or more objects in the image and determine the position and orientation of such objects.
While vision technology has improved significantly in the past few years, most of the improvements relate to processing of the image data captured by vision sensors and may be attributed to the use of big data, sophisticated machine learning algorithms like convolutional neural networks (CNNs) and graphical processing units (GPUs) for processing of the image data. The conventional vision technology however, has significant limitations specifically with respect to capturing of the raw data about an object or a scene. For example, the optical lenses in conventional vision systems attempt to extract information in a linear and obtuse way by relying on simple focusing techniques. The attempt to get an object into focus on an image ends up losing a large amount of information and other optical properties. A need exists for capturing previously lost or inferred information so as to generate an image that is not âperfectâ to the eye, but rich to algorithms. A further need exists for a richer object recognition complex vision application where conventional vision technologies have proved inadequate including recognizing objects in dynamic environments like when the object or vision system are moving, as in a mobile, robotic usage example; recognizing three dimensional (3D) objects by capturing depth data; predicting object attributes like depth, orientation, and motion; recognizing tiny objects; recognizing facial features; recognizing objects in a power constrained or network constrained environment, and other use cases for which traditional machine vision systems and methods are poorly suited.
Furthermore, automation is revolutionizing value chains for almost all categories of items, and robotics is at the heart of the revolution. While physical robots have played an ever-expanding role in manufacturing for years, typical implementations have historically focused on fixed location robots completing prescribed tasks in pre-defined arrangements, such as painting, welding, and so forth in an assembly line. These limited roles produced and continue to produce significant improvements in quality, cost, and productivity, but do not take full advantage of emerging technologies in engineering, materials science, software process automation, artificial intelligence, additive manufacturing, data-driven analytics, digital twins, blockchains, smart contracts, and the like. These technologies can be integrated with developments in robotics (including hardware and software robotics) to produce an innovative array of highly functional autonomous robots with interactive capabilities. Emerging and future robot classes and capabilities provide opportunity for ever-expanding robot use cases and management platforms that can automatically configure, organize, deploy, and control robots and robot fleets to securely deliver reliable services, including contracted services that access robotic fleet capabilities in ârobotics-as-a-serviceâ platforms, among others.
SUMMARY
A robot fleet management platform includes a set of datastores that store a governance library that defines a set of governance standards that include at least one set of security standards, legal standards, ethical standards, regulatory standards, quality standards, or engineering standards that are applied to decisions made by one or more respective intelligence services. The robot fleet management platform includes a set of one or more processors that execute a set of computer-readable instructions. The set of one or more processors collectively execute a governance-enabling intelligence layer that receives and responds to intelligence requests received from respective intelligence service clients. The intelligence layer includes a set of artificial intelligence services that includes at least one of a machine learning service, a rules-based intelligence service, a digital twin service, a robot process automation service, or a machine vision service. The intelligence layer includes an intelligence layer controller that coordinates performance of respective intelligence services on behalf of the respective intelligence service clients and performance of a set of analyses corresponding to the respective intelligence services based in part on the set of governance standards. The intelligence layer returns decisions determined collectively by the artificial intelligence service in response to the intelligence requests, such that the decisions are determined based on a set of intelligence service data sources and the set of analyses.
In other features, the intelligence layer controller is configured to receive an intelligence request from an intelligence service client indicating a requested decision, determine zero or more governance standards that are implicated by a type of the requested decision, determine zero or more pre-defined analyses that are implicated by the type of the requested decision or by a governance standard implicated by the type of decision, and provide the zero or more governance standards and the zero or more pre-defined analyses to the artificial intelligence service. The zero or more governance standards are selected from the governance standards defined in the governance library.
In other features, the intelligence layer controller is further configured to iteratively determine and provide additional governance standards and pre-defined analyses to the artificial intelligence service in response to determinations made by the artificial intelligence service until the requested decision is provided by the artificial intelligence service. In other features, the intelligence layer is further configured to determine the set of intelligence layer data sources based on the type of the requested decision. In other features, a requesting intelligence service client provides the set of intelligence layer data sources with the request. In other features, the decisions provided by the intelligence layer define respective actions to be taken by the respective intelligence service clients. In other features, the respective actions include an action to request human intervention.
In other features, the respective actions include non-adaptive pre-defined actions. In other features, the respective actions includ
CROSS-REFERENCE TO RELATED APPLICATIONS
This application is a continuation of PCT/US2021/064233 filed Dec. 17, 2021, which claims the benefit of U.S. Provisional App. No. 63/127,983 filed Dec. 18, 2020 and U.S. Provisional App. No. 63/185,348 filed May 6, 2021 and claims priority to India App. No. IN202111029964 filed Jul. 3, 2021 and India App. No. IN202111036187 filed Aug. 10, 2021. The entire disclosures of the above applications are incorporated by reference.
FIELD
The present disclosure relates to information technology methods and systems for management of value chain network entities, including supply chain and demand management entities. The present disclosure also relates to the field of enterprise management platforms, more particularly involving data management, artificial intelligence, network connectivity and digital twins, additive manufacturing, robotics-as-a-service, and energy management.
BACKGROUND
Historically, many of the various categories of goods purchased and used by household consumers, by businesses and by other customers were supplied mainly through a relatively linear fashion, in which manufacturers and other suppliers of finished goods, components, and other items handed off items to shipping companies, freight forwarders and the like, who delivered them to warehouses for temporary storage, to retailers, where customers purchased them, or directly to customer locations. Manufacturers and retailers undertook various sales and marketing activities to encourage and meet demand by customers, including designing products, positioning them on shelves and in advertising, setting prices, and the like.
Orders for products were fulfilled by manufacturers through a supply chain, such as depicted in FIG. 1 , where suppliers 122 in various supply environments 160 , operating production facilities 134 or acting as resellers or distributors for others, made a product 130 available at a point of origin 102 in response to an order. The product 130 was passed through the supply chain, being conveyed and stored via various hauling facilities 138 and distribution facilities 134 , such as warehouses 132 , fulfillment centers 112 and delivery systems 114 , such as trucks and other vehicles, trains, and the like. In many cases, maritime facilities and infrastructure, such as ships, barges, docks and ports provided transport over waterways between the points of origin 102 and one or more destinations 104 .
Organizations have access to an almost unlimited amount of data. With the advent of smart connected devices, wearable technologies, the Internet of Things (IoT), and the like, the amount of data available to an organization that is planning, overseeing, managing and operating a value chain network has increased dramatically and will likely to continue to do so. For example, in a manufacturing facility, warehouse, campus, or other operating environment, there may be hundreds to thousands of IoT sensors that provide metrics such as vibration data that measure the vibration signatures of important machinery, temperatures throughout the facility, motion sensors that can track throughput, asset tracking sensors and beacons to locate items, cameras and optical sensors, chemical and biological sensors, and many others. Additionally, as wearable technologies become more prevalent, wearables may provide insight into the movement, health indicators, physiological states, activity states, movements, and other characteristics of workers. Furthermore, as organizations implement CRM systems, ERP systems, operations systems, information technology systems, advanced analytics and other systems that leverage information and information technology, organizations have access to an increasingly wide array of other large data sets, such as marketing data, sales data, operational data, information technology data, performance data, customer data, financial data, market data, pricing data, supply chain data, and the like, including data sets generated by or for the organization and third-party data sets.
The presence of more data and data of new types offers many opportunities for organizations to achieve competitive advantages; however, it also presents problems, such as of complexity and volume, such that users can be overwhelmed, missing opportunities for insight. A need exists for methods and systems that allow enterprises not only to obtain data, but to convert the data into insights and to translate the insights into well-informed decisions and timely execution of efficient operations.
Additive Manufacturing
Additive manufacturing, encompassing technologies like 3D printing, vapor deposition, polymer (or other material) coating, epitaxial and/or crystalline growth approaches, and others, alone or in combination with other technologies, such as subtractive or assembly technologies, enables manufacturing of a three-dimensional product from a design via a process of forming successive layers of the product, with optional interim or subsequent steps to arrive at a finished component or system. The design may be in the form of a data source like an electronic 3D model created with a computer aided design package or via 3D scanner. The 3D printing or other additive process then involves forming a first material-layer and then adding successive material layers wherein each new material-layer is added on a pre-formed material-layer, until the entire designed three-dimensional product is completed. References to 3D printing or other particular additive manufacturing technologies throughout this disclosure should be understood to encompass alternative embodiments involving other additive manufacturing technologies, except where context specifically indicates otherwise.
A large number of additive processes are currently available. They may differ in the manner successive layers are deposited to create the 3D product. They may also differ in terms of materials that are used to form the product. Metals (such term including alloys except where context specifically indicates otherwise and including specialized metals such as shape memory materials) are increasingly popular 3D printing materials. Common ones include Titanium, Stainless steel, Aluminum, Tool Steel, Inconel and Cobalt Chrome. Some methods melt or soften metal to produce the layers. Examples of metal 3D printing methods include selective laser melting (SLM), selective laser sintering (SLS), direct metal laser sintering (DMLS) and/or fused deposition modeling (FDM). Other methods include: (a) metal extrusion where a filament or rod consisting of polymer and heavily loaded with metal powder is extruded through a nozzle (like in FDM) to form the âgreenâ part that is post-processed (debinded and sintered) to create a fully-metal part; (b) metal binder jetting that uses print-heads to apply a liquid binding agent onto layers of powder and (c) nanoparticle jetting that uses jetting of metal nanoparticles from inkjet nozzles in super-thin layers.
Regardless of the design data sources or the methods employed for additive manufacturing, including metal 3D printing, the entire process from design and manufacturing to end customer delivery, remains prone to inefficiency, process variations, product inconsistency, and unreliability. This can result in a final 3D printed product that does not meet customer expectations and/or product specifications, and it can lead to low quality 3D printed products or components that result in failures, among other problems. These issues can also increase operating costs for 3D printing service providers through material waste, reduced throughput due to machine downtime and/or unproductive print hours, and associated supply chain risks and inefficiencies. For example, it is common for 3D printed products to get deformed during or after the manufacture due to printing procedures and non-optimized printing parameters. Also, common issues that can arise due to inefficient manufacturing supply chains include fraud, delayed deliveries, contractual liability, and product recalls.
To ensure that the final metal 3D printed product matches the customer expectations and producer specifications around quality, cost and turnaround time, a need exists for smarter product design, manufacturing, supply chain and demand management methods and systems. A further need exists for methods and systems that allow for improved monitoring, management, and optimization of additive manufacturing capabilities by and for various interested parties.
Conventional machine vision systems are made of a combination of optics, lighting, sensors and software and aim to replicate the function of human eye. Such systems create an image of an object by capturing and analyzing the reflected light from the object. An optical lens captures the image and presents it to an image sensor such as a charge coupled device (CCD) or complementary metal oxide semiconductor (CMOS) device. Such devices contain matrices or linear arrays of small, accurately spaced photo sensitive elements fabricated on silicon chips using integrated circuit technology. The sensor device converts the light falling on it, through the camera lens, into analog electrical signal corresponding to light intensity. The object image is thus broken down into an array of individual picture elements or pixels. An analog to digital converter is used to convert analog voltage of element into digital value. If voltage level for each pixel is given either 0 or 1 value depending on some threshold value, it is called binary system. On the other hand, a gray scale system assigns up to 256 different values depending on intensity to each pixel. Thus, in addition to black and white, many different shades of gray can be distinguished. A gray-scale image may be seen to have one channel, represented by a 2-D matrix of pixels having pixel values in the range of, for example, 0 to 255. A color image on the other hand represents the brightness and color of the pixels in an image by the three primary color values: R (red), G (green), and B (blue). Thus, color images have red, green, and blue (RGB) channels each representing RGB components of the image. This raw data captured by the image sensor is then sent to an image processing system for analysis. The image processing system then processes the raw data to extract useful information to analyze the image and make decisions on such analysis. The image processing system may include a pre-processing function to enhance the image quality. For example, such processing may involve image scaling, noise reduction, color adjustment, brightness adjustment, white balance adjustment, sharpness, adjustment, contrast adjustment and the like. Further the image may be analyzed using machine learning or other algorithms to identify one or more objects in the image and determine the position and orientation of such objects.
While vision technology has improved significantly in the past few years, most of the improvements relate to processing of the image data captured by vision sensors and may be attributed to the use of big data, sophisticated machine learning algorithms like convolutional neural networks (CNNs) and graphical processing units (GPUs) for processing of the image data. The conventional vision technology however, has significant limitations specifically with respect to capturing of the raw data about an object or a scene. For example, the optical lenses in conventional vision systems attempt to extract information in a linear and obtuse way by relying on simple focusing techniques. The attempt to get an object into focus on an image ends up losing a large amount of information and other optical properties. A need exists for capturing previously lost or inferred information so as to generate an image that is not âperfectâ to the eye, but rich to algorithms. A further need exists for a richer object recognition complex vision application where conventional vision technologies have proved inadequate including recognizing objects in dynamic environments like when the object or vision system are moving, as in a mobile, robotic usage example; recognizing three dimensional (3D) objects by capturing depth data; predicting object attributes like depth, orientation, and motion; recognizing tiny objects; recognizing facial features; recognizing objects in a power constrained or network constrained environment, and other use cases for which traditional machine vision systems and methods are poorly suited.
Furthermore, automation is revolutionizing value chains for almost all categories of items, and robotics is at the heart of the revolution. While physical robots have played an ever-expanding role in manufacturing for years, typical implementations have historically focused on fixed location robots completing prescribed tasks in pre-defined arrangements, such as painting, welding, and so forth in an assembly line. These limited roles produced and continue to produce significant improvements in quality, cost, and productivity, but do not take full advantage of emerging technologies in engineering, materials science, software process automation, artificial intelligence, additive manufacturing, data-driven analytics, digital twins, blockchains, smart contracts, and the like. These technologies can be integrated with developments in robotics (including hardware and software robotics) to produce an innovative array of highly functional autonomous robots with interactive capabilities. Emerging and future robot classes and capabilities provide opportunity for ever-expanding robot use cases and management platforms that can automatically configure, organize, deploy, and control robots and robot fleets to securely deliver reliable services, including contracted services that access robotic fleet capabilities in ârobotics-as-a-serviceâ platforms, among others.
SUMMARY
A robot fleet management platform includes a set of datastores that store a governance library that defines a set of governance standards that include at least one set of security standards, legal standards, ethical standards, regulatory standards, quality standards, or engineering standards that are applied to decisions made by one or more respective intelligence services. The robot fleet management platform includes a set of one or more processors that execute a set of computer-readable instructions. The set of one or more processors collectively execute a governance-enabling intelligence layer that receives and responds to intelligence requests received from respective intelligence service clients. The intelligence layer includes a set of artificial intelligence services that includes at least one of a machine learning service, a rules-based intelligence service, a digital twin service, a robot process automation service, or a machine vision service. The intelligence layer includes an intelligence layer controller that coordinates performance of respective intelligence services on behalf of the respective intelligence service clients and performance of a set of analyses corresponding to the respective intelligence services based in part on the set of governance standards. The intelligence layer returns decisions determined collectively by the artificial intelligence service in response to the intelligence requests, such that the decisions are determined based on a set of intelligence service data sources and the set of analyses.
In other features, the intelligence layer controller is configured to receive an intelligence request from an intelligence service client indicating a requested decision, determine zero or more governance standards that are implicated by a type of the requested decision, determine zero or more pre-defined analyses that are implicated by the type of the requested decision or by a governance standard implicated by the type of decision, and provide the zero or more governance standards and the zero or more pre-defined analyses to the artificial intelligence service. The zero or more governance standards are selected from the governance standards defined in the governance library.
In other features, the intelligence layer controller is further configured to iteratively determine and provide additional governance standards and pre-defined analyses to the artificial intelligence service in response to determinations made by the artificial intelligence service until the requested decision is provided by the artificial intelligence service. In other features, the intelligence layer is further configured to determine the set of intelligence layer data sources based on the type of the requested decision. In other features, a requesting intelligence service client provides the set of intelligence layer data sources with the request. In other features, the decisions provided by the intelligence layer define respective actions to be taken by the respective intelligence service clients. In other features, the respective actions include an action to request human intervention.
In other features, the respective actions include non-adaptive pre-defined actions. In other features, the respective actions include domain-specific actions that are responsive to the respective requests. In other features, the intelligence service clients include a security system that requests classifications of potential security risks. In other features, the intelligence service clients include a resource provisioning system that requests recommendations for resources to support a robot fleet. In other features, the intelligence service clients include a logistics system that requests logistics-based recommendations with respect to one or more robot fleets. In other features, the intelligence service clients include a job configuration system that requests proposed job configurations given a job request. In other features, the intelligence service clients include a fleet configuration system that requests proposed fleet configurations given a set of tasks to be completed by a robot fleet. In other features, the intelligence service clients include a robot operating unit deployed by the robot fleet management platform.
A robot fleet management platform for configuring robot fleet resources includes a set of one or more processors that execute a set of computer-readable instructions. The set of one or more processors collectively execute a job parsing system that applies a set of filters to job content received in association with a job request to identify portions thereof suitable for robot automation. A task definition system establishes a set of robot tasks that each define at least a type of robot and a task objective, the set of robot tasks being based at least in part on the portions of the job request that are suitable for robot automation and meet a first fleet objective of a set of fleet objectives. A fleet configuration proxy service processes the set of robot tasks and additional job content relating to the job request to produce a fleet resource configuration data structure for the job request that defines a set of task associations and a set of robot adaptation instructions. Each task association associates at least one robot operating unit to a respective robot task of the set of robot tasks and the set of robot adaptation instructions define a manner by which one or more robot operating units of a robot fleet are to be adapted to perform respective tasks to which robots are assigned. A fleet intelligence layer activates a set of intelligence services to produce at least one recommended robot task and associated contextual information that facilitates robot selection and task ordering in a workflow of robot tasks. A job workflow system generates a workflow that defines an order of performance of the robot tasks based on the fleet resource configuration data structure and the set of robot tasks. A workflow simulation system is configured to simulate performance of the job based on the workflow and a job execution simulation environment. The workflow simulation system applies the workflow in the job execution simulation environment that includes digital models of the robot operating units assigned to the robot fleet and digital models of the task definitions to produce a simulation result, such that the simulation result is used to iteratively redefine one or more of the set of tasks, the fleet resource configuration data structure, or the workflow until the simulation result satisfies a second fleet objective of the set of fleet objectives corresponding to the job request. A job execution plan generator, in response to the simulation result satisfying the set of fleet objectives, generates a job execution plan based on the set of tasks, the fleet resource configuration data structure, and the workflow.
In other features, the task definition system interacts with the intelligence layer to suggest alternate tasks that meet a second fleet objective. In other features, the task definition system interacts with the intelligence layer to optimize at least one of a robot type and a task objective based on the first fleet objective. In other features, the first fleet objective includes fleet resource utilization criteria. In other features, the task definition system receives from the fleet configuration proxy service a particular robot type for use when performing the robot task. In other features, the task definition system configures the set of robot tasks based on the particular robot type provided by the fleet configuration proxy service. In other features, the task definition system generates a data structure for each task in the set of tasks that includes a reference to a digital twin for at least one of the task and at least one robot operating unit for performing the tasks for use by the workflow simulation system. In other features, the task definition system generates a data structure for each task in the set of tasks that identifies at least one a type of robot and a robot operating unit for performing the task and a configuration data structure for configuring a robot for performing the task. In other features, the task definition system generates a data structure for each task in the set of tasks and stores the data structure in a library of robot tasks that is indexed by information indicative of the job request and an identifier of at least one of the robot type and the robot operating unit. In other features, the task definition system matches requirements for constraints identified in the job request with robot capabilities when identifying the type of robot for meeting the task objective. In other features, the task definition system generates a plurality of robot tasks for a plurality of different robot types to achieve a task objective.
In other features, the task definition system queries a library of robot tasks for candidate robot tasks that satisfy the task objective and interacts with the fleet configuration proxy service to select a robot tasks from the candidate robot tasks based on the at least one fleet objective. In other features, the at least one fleet objective is compatibility with available robot operating units. In other features, the task definition system queries a library of robot tasks for candidate robot tasks that satisfy the task objective and interacts with the fleet intelligence layer to select a robot task from the candidate robot tasks based on a suitability of the candidate robot tasks for achieving the task objective. In other features, the task definition system references information descriptive of sensor detection packages that indicate preferred sequences of sensing tasks when defining the set of tasks. In other features, the job workflow system references information descriptive of sensor detection packages that indicate preferred sequences of sensing tasks when defining the workflow of robot tasks. In other features, the job workflow system generates the workflow of robot tasks based on second task dependency on a first task for meeting an objective of the second task. In other features, the job workflow simulation system operates digital twins of tasks in the set of tasks for determining an optimized workflow order of tasks.
A robot fleet management platform for configuring robot fleet resources includes a set of one or more processors that execute a set of computer-readable instructions. The set of one or more processors collectively execute a job configuration system that receives a job request and determines a set of robot tasks to be performed by a robot fleet based on job content associated with the job request and at least one fleet objective in a set of fleet objectives. A fleet configuration proxy service applies fleet configuration services to the set of robot tasks and the job content to produce a fleet resource configuration data structure for the job request. A fleet intelligence layer activates a set of intelligence services to produce at least one recommended robot task and associated contextual information that facilitates robot selection and task ordering in a workflow of robot tasks. A job workflow system generates a workflow that defines an order of performance of the robot tasks based on the fleet resource configuration data structure and the set of robot tasks. A workflow simulation system is configured to simulate performance of the job based on the workflow and a job execution simulation environment to produce a simulation result that is used to recursively redefine one or more of the set of tasks, the fleet resource configuration data structure, or the workflow until the simulation result satisfies a second fleet objective of the set of fleet objectives corresponding to the job request. A job execution plan generator, in response to the simulation result satisfying the set of fleet objectives, generates a job execution plan based on the set of tasks, the fleet resource configuration data structure, and the workflow.
In other features, the job configuration system includes a job parsing system that applies content and structural filters to job content received in association with a job request to identify portions thereof suitable for robot automation. In other features, the job configuration system includes a task definition system that establishes a set of robot tasks that each define at least a type of robot and a task objective, the set of robot tasks are based at least in part on the portions of the job request that are suitable for robot automation and meet a first fleet objective of the set of fleet objectives. In other features, the fleet resource configuration data structure defines a set of task associations and a set of robot adaptation instructions. Each task association associates at least one robot operating unit to a respective robot task of the set of robot tasks and the set of robot adaptation instructions define a manner by which one or more robot operating units of a robot fleet are to be adapted to perform respective tasks to which the robots are assigned. In other features, the workflow simulation system applies the workflow in the job execution simulation environment that includes digital models of the robot operating units assigned to the robot fleet and digital models of the task definitions to produce the simulation result. In other features, the job configuration system interacts with the intelligence layer to suggest alternate tasks that meet a second fleet objective. In other features, the job configuration system interacts with the intelligence layer to optimize at least one of a robot type and a task objective based on at least one of the set of fleet objectives. In other features, the first fleet objective includes fleet resource utilization criteria.
In other features, the job configuration system receives from the fleet configuration proxy service a particular robot type for use when performing the robot task. In other features, the job configuration system configures the set of robot tasks based on the particular robot type provided by the fleet configuration proxy service. In other features, the job configuration system generates a data structure for each task in the set of tasks that includes a reference to a digital twin for at least one of the task and at least one robot operating unit for performing the tasks for use by the workflow simulation system. In other features, the job configuration system generates a data structure for each task in the set of tasks that identifies at least one a type of robot and a robot operating unit for performing the task and a configuration data structure for configuring a robot for performing the task. In other features, the job configuration system generates a data structure for each task in the set of tasks and stores the data structure in a library of robot tasks that is indexed by information indicative of the job request and an identifier of at least one of the robot type and the robot operating unit. In other features, the job configuration system matches requirements for constraints identified in the job request with robot capabilities when identifying the type of robot for meeting the task objective. In other features, the job configuration system generates a plurality of robot tasks for a plurality of different robot types to achieve a task objective. In other features, the job configuration system queries a library of robot tasks for candidate robot tasks that satisfy the task objective and interacts with the fleet configuration proxy service to select a robot tasks from the candidate robot tasks based on the at least one fleet objective.
In other features, the at least one fleet objective is compatibility with available robot operating units. In other features, the job configuration system queries a library of robot tasks for candidate robot tasks that satisfy the task objective and interacts with the fleet intelligence layer to select a robot task from the candidate robot tasks based on a suitability of the candidate robot tasks for achieving the task objective. In other features, the job configuration system references information descriptive of sensor detection packages that indicate preferred sequences of sensing tasks when defining the set of tasks. In other features, the job workflow system references information descriptive of sensor detection packages that indicate preferred sequences of sensing tasks when defining the workflow of robot tasks. In other features, the job workflow system generates the workflow of robot tasks based on second task dependency on a first task for meeting an objective of the second task. In other features, the job workflow simulation system operates digital twins of tasks in the set of tasks for determining an optimized workflow order of tasks.
A robot fleet management platform includes a set of one or more processors that execute a set of computer-readable instructions. The set of one or more processors collectively execute receiving a job request includes information descriptive of job deliverable and request-specific constraints for delivering the job deliverable. Also executed is applying content and structural filters to content received in association with a job request to identify portions thereof suitable for robot automation. Also executed is establishing a set of robot tasks that each define at least a type of robot and a task objective, the set of robot tasks are based at least in part on the portions of the job request that are suitable for robot automation and meet a first fleet objective. Also executed is applying fleet configuration services to the job content and the set of robot tasks to produce a fleet resource configuration data structure for the job request that associates at least one robot operating unit with each task in the set of tasks and, based on the at least one robot operating unit, robot adaptation instructions for performing the associated task. Also executed is recommending robot task and associated contextual information that facilitates robot selection and task ordering in a workflow of robot tasks with a fleet intelligence layer. Also executed is generating a workflow of the robot tasks based on the fleet resource configuration data structure and the set of robot tasks. Also executed is simulating digital models of the robot operating units performing digital models of the task definitions thereby validating the generated workflow while providing a result of the job execution simulation for recursively establishing the set of robot tasks. Also executed is generating at least a first portion of an execution plan for robot fleet resources configured in the fleet resource configuration data structure.
In other features, the robot fleet management platform includes suggesting alternate tasks that meet a second fleet objective with the fleet intelligence layer. In other features, the robot fleet management platform includes optimizing at least one of a robot type and a task objective with the intelligence layer based on the first fleet objective. In other features, the first fleet objective includes fleet resource utilization criteria. In other features, the task definition system receives from the fleet configuration proxy service a particular robot type for use when performing the robot task. In other features, establishing the set of robot tasks is based on the particular robot type provided by the fleet configuration proxy service. In other features, establishing the set of robot tasks includes generating a data structure for each task in the set of tasks that includes a reference to a digital twin for at least one of the task and at least one robot operating unit for performing the tasks for use by the workflow simulation system. In other features, establishing the set of robot tasks includes generating a data structure for each task in the set of tasks that identifies at least one a type of robot and a robot operating unit for performing the task and a configuration data structure for configuring a robot for performing the task. In other features, establishing the set of robot tasks includes generating a data structure for each task in the set of tasks and stores the data structure in a library of robot tasks that is indexed by information indicative of the job request and an identifier of at least one of the robot type and the robot operating unit.
In other features, establishing the set of robot tasks includes matching requirements for constraints identified in the job request with robot capabilities when identifying the type of robot for meeting the task objective. In other features, establishing the set of robot tasks includes generating a plurality of robot tasks for a plurality of different robot types to achieve a task objective. In other features, establishing the set of robot tasks includes querying a library of robot tasks for candidate robot tasks that satisfy the task objective and interacts with the fleet configuration proxy service to select a robot tasks from the candidate robot tasks based on the at least one fleet objective. In other features, the at least one fleet objective is compatibility with available robot operating units. In other features, establishing the set of robot tasks includes querying a library of robot tasks for candidate robot tasks that satisfy the task objective and interacts with the fleet intelligence layer to select a robot task from the candidate robot tasks based on a suitability of the candidate robot tasks for achieving the task objective. In other features, establishing the set of robot tasks includes referencing information descriptive of sensor detection packages that indicate preferred sequences of sensing tasks when defining the set of tasks. In other features, generating the workflow of the robot tasks includes referencing information descriptive of sensor detection packages that indicate preferred sequences of sensing tasks when defining the workflow of robot tasks. In other features, generating the workflow of the robot tasks is based on second task dependency on a first task for meeting an objective of the second task. In other features, simulating digital models of the robot operating units includes operating digital twins of tasks in the set of tasks for determining an optimized workflow order of tasks.
A robot fleet platform is for preparing a job request for facilitating configuration of a robot fleet operated by the robot fleet platform. The system includes a set of one or more processors that execute a set of computer-readable instructions. The set of one or more processors collectively execute a job request ingestion system configured to receive job content relating to at least one of picking, packing, moving, storing, warehousing, transporting or delivering of a set of items in a supply chain, the job content including an electronic job request and related data. A job content parsing system is configured to apply filters to the received job content to identify candidate portions thereof for robot automation. A fleet intelligence layer activates a set of intelligence services to process terms in the candidate portions of the job content and receive therefrom at least one recommended robot task and associated contextual information that facilitates robot selection and task ordering in a workflow of robot tasks. A demand intelligence layer provides real time information relating to a parameter of demand for the set of items in the supply chain. A job requirements system produces a set of job request instance-specific job requirements based on the portions of the job content that indicate robot automation, the real time information from the demand intelligence layer and the at least one recommended robot task and associated contextual information. The set of job requirements is stored in a non-transitory computer readable memory that is accessible by at least one processor of the set of processors.
In other features, the job content parsing system retrieves a set of content and structural filters from a job configuration library that facilitates mapping indicia of the job content with target terms that indicate robot automation. In other features, the job content parsing system augments a set of default content and structural filters with filter criteria from a job configuration library that facilitates mapping indicia of the job content with target terms that indicate robot automation. In other features, the content filter indicates terms in the job content that distinguish robot automation content from other content in the job content. In other features, the terms are retrieved from a job configuration library that facilitates mapping indicia of the job content with terms that indicate robot automation. In other features, the fleet intelligence layer facilitates sending portions of the job content identified as suitable for robot automation to a machine learning service of the set of intelligence services for improving job content parsing. In other features, the machine learning service is trained with training data sets includes human-generated feedback on job content parsing results for a plurality of job requests, robot automation knowledge bases, desired job-specific knowledge bases, technical dictionaries, and content received from job experts. In other features, the job parsing system is configured to detect physical location information in the job content that facilitates automatically determining at least one of transportation options, operational constraints, permitting requirements, transport restrictions, fleet assets that are local to a physical location of the job request, and logistics constraints.
In other features, the physical location information includes one or more of an address, a region, GPS data, aerial photography, a marked location on a map image, map coordinates, latitude, longitude, altitude, a route, a depth relative to sea level. In other features, the job parsing system is configured to detect electrical power information for at least one location in the job content including a plurality of voltages, frequencies, currents, schedules of availability, schedules of grid-provided electricity costs, cost per kwh, a power demand profile, a maximum thermal density, and proximity to the at least one location. In other features, the job parsing system is configured to detect digital data representative of a layout of a portion of a job site that is present or referenced in the job content to facilitate generating at least one job request instance-specific requirement associated with job site layout. In other features, the job parsing system is configured to detect at least one of information descriptive of an operating environment, deliverables, interfaces through which information about the job request is communicated with a job requester, wireless communication network accessibility, budget constraints for performing tasks, and scheduling of resources in regards to access and operation at a job site. In other features, the job request ingestion system is configured to scan received job content for external links to related data. In other features, the job request ingestion system is configured to retrieve related data for use by the robot fleet platform based on the external links. In other features, the job request ingestion system is configured to determine and forward to a job content parsing system portions of job content received that include references to activities suitable for being performed by a robotic fleet resource.
In other features, the job request ingestion system is configured to process content received with a job configuration indicia filter that automatically routes job configuration indicia in the job content to a job configuration library look up service for classifying the job configuration indicia as one of a current job configuration, a prior job configuration, or an unknown job configuration. In other features, the job content parsing system is configured to identify structural and content elements in the received content that facilitate identification of candidate robot tasks. In other features, the job content parsing system is configured to identify structural elements in the received content that indicate at least one of tasks, sub tasks, task ordering, task dependencies, and task requirements for facilitating selection of fleet robot operating units. In other features, the job content parsing system is configured to identify content terms indicative of at least one robot minimum capacity. In other features, the job content parsing system is configured with a robot type filter that when applied to the job request content identifies terms indicative of a type of robot for performing a task. In other features, the job request ingestion system includes a job request ingestion interface for receiving the electronic job request. In other features, applying the content and structural filters includes scanning received content for data indicative of robot activities. In other features, applying the content and structural filters with the job content parsing system includes processing received content with a robot type filter that when applied to the job request content identifies terms indicative of a type of robot for performing a task.
In other features, the job parsing system utilizes the content filters to detect qualified job data. In other features, the robot fleet platform includes a qualified data query generation system configured to generate a query regarding at least one element of qualified data in the job content for clarification thereof. In other features, the query regarding the at least one element of qualified data is presented in the user interface. In other features, the query regarding at least one element of qualified data is provided to the fleet intelligence layer for processing with at least one intelligence service of the set of intelligence services to provide at least one clarification item of data for the at least one element of qualified data through the fleet intelligence layer. In other features, the robot fleet platform includes a qualified data resolution system configured to evaluate at least one qualified data element in the job content for similarity to clarified data from a plurality of job requests, and based on an outcome of the evaluation to adjust the at least one qualified data element based on a similar clarified data element. In other features, adjusting the at least one qualified data element includes replacing a qualified data value in the qualified data element with a corresponding data value from the clarified data element. In other features, the content filters are configured to identify qualified data, including at least one of missing data, unclear data and qualitative references. In other features, the fleet intelligence layer facilitates processing qualified data with a machine learning service of the set of intelligence services for improving parsing of qualified data. In other features, the content filters are configured to identify qualified data and related context for facilitating resolution of at least one of missing data, unclear data and qualitative references in the qualified data.
A value chain network automation system includes a supply chain robotic fleet data set including attributes of a set of states and capabilities of a set of robotic systems in a supply chain for a set of goods. The system includes a demand intelligence robotic process automation data set including attributes of a set of states of a set of robotic process automation systems that undertake automation of a set of demand forecasting tasks for the set of goods. The system includes a coordination system that provides a set of robotic task instructions for the supply chain robotic fleet based on processing the supply chain robotic fleet data set and the demand intelligence robotic process automation data set to coordinate supply and demand for the set of goods.
FURTHER SUMMARY
According to some embodiments of the present disclosure, methods and systems are provided herein for an information technology system that may include a cloud-based management platform with a micro-services architecture; a set of interfaces, network connectivity facilities, adaptive intelligence facilities, data storage facilities, and monitoring facilities; and a set of applications for enabling an enterprise to manage a set of value chain network entities from a point of origin to a point of customer use.
Among other things, provided herein are methods, systems, components, processes, modules, blocks, circuits, sub-systems, articles, services, software, hardware, and other elements (collectively referred to in some cases as the âplatformâ or the âsystem,â which terms should be understood to encompass any of the above except where context indicates otherwise) that individually or collectively improve the utilization of additive manufacturing capabilities in a network of value chain entities in a value chain network (such terms encompassing the many examples and embodiments disclosed herein and in the documents incorporated by reference herein).
In embodiments, such methods and systems allow for feedback and monitoring by the customer and various other interested parties throughout the modelling, printing and supply chain processes resulting in optimizing 3D printing parameters, achieving greater fidelity and accuracy in printing and enhancing efficiency and traceability of design processes, manufacturing, supply chains demand management systems, products, and product use cases among others.
Aspects provided herein include an information technology system having an artificial intelligence system for learning on a training set of outcomes, parameters, and data collected from a set of distributed manufacturing network entities in a distributed manufacturing network and/or value chain network to optimize digital production processes and workflows.
Aspects provided herein include an information technology system for a distributed manufacturing network, comprising an additive manufacturing management platform configured for managing process and production workflows for a set of distributed manufacturing network entities through design, modelling, printing, supply chain, delivery, point-of-sale and point of usage stages; an artificial intelligence system configured for learning on a training set of outcomes, parameters, and data collected from the distributed manufacturing network entities of the distributed manufacturing network to optimize digital production processes and workflows; and a distributed ledger system integrated with a digital thread configured for providing unified views of workflow and transaction information to entities in the distributed manufacturing network.
In embodiments, the information technology system comprises a control system configured to adjust the data and one or more parameters collected from the distributed manufacturing network entities in real time.
In embodiments, the information technology system comprises a digital twin system configured to build a digital twin of one or more distributed manufacturing network entities, the digital twin providing a substantially real-time representation of the distributed manufacturing network entity through data from one or more sensors positioned in, on or near the distributed manufacturing network entity. In embodiments, the digital twin may represent various parameters and attributes of the manufacturing entity (whether an additive, subtractive, biological, chemical, or other entity), such as the types of materials it can handle, current levels of available source materials, processing/output speed, operating capabilities, biological manufacturing capability, vacuum processing capability, energy production and consumption information (e.g., for heating, laser processing, and the like), pricing parameters, and the like. In embodiments, the platform, such as using an artificial intelligence system, may execute simulations on the digital twin or projected outputs thereof for predicting a possible future state of the distributed manufacturing network entity and/or one or more outputs thereof.
In embodiments, the distributed manufacturing network entities include a set of printed parts, products, processes, additive manufacturing units like 3D printers, other types of manufacturing units, parties (e.g., suppliers, manufacturers, financiers, users, customers and others), packagers, infrastructure, vehicles, and manufacturing nodes.
Aspects provided herein include a distributed manufacturing network comprising: an additive manufacturing management platform with an artificial intelligence system configured to learn on a training set of outcomes, parameters, and data collected from a set of distributed manufacturing network entities for optimizing manufacturing, supply chain, demand management, service, maintenance and other processes and workflows; and a distributed ledger integrated with digital threads of the distributed manufacturing network entities.
In embodiments, the distributed network entity is a part being manufactured using additive manufacturing and the digital thread constitutes information related to the complete lifecycle of the part from design, modeling, production, validation, use and maintenance through disposal. In embodiments, a digital thread may include a set of instructions for manufacturing an item that includes additive manufacturing instructions, such as design specifications and/or operating parameters by which one or more additive manufacturing units may be configured and operated to produce the item. In embodiments, a digital thread may include multiple alternative such instruction sets, such as ones that are configured to facilitate manufacturing of the item by alternative forms of additive manufacturing and/or hybrid or combinations thereof with other additive manufacturing types and/or with other manufacturing types. In embodiments, the instruction sets are embodied in a set of digital twins.
Aspects provided herein include an autonomous additive manufacturing platform comprising: a plurality of sensors positioned in, on, and/or near a product or a part and configured to collect sensor data related to the product or the part, the sensor data being substantially real-time sensor data; an adaptive intelligence system connected to the plurality of sensors and configured to receive the sensor data from the plurality of sensors, the adaptive intelligence system including: a machine learning system configured to input the sensor data into one or more machine learning models, the sensor data being used as training data for the machine learning models, the machine learning models being configured to transform the sensor data into simulation data; and a digital twin system configured to create a product twin or a part twin based on the simulation data, the product twin or the part twin providing for substantially real-time representation of the product or the part and providing for simulation of a possible future state of the product or the part via the simulation data; and an artificial intelligence system configured to execute simulations on the digital twin system; wherein the one or more models are utilized by the artificial intelligence system to make classifications, predictions, recommendations, and/or to generate or facilitate decisions or instructions relating to the product and the part, such as decisions or instructions governing design, configuration, material selection, shape selection, manufacturing type, job scheduling and many others.
In embodiments, the models trained by the machine learning system are utilized by the artificial intelligence system to execute simulations on the part twin for predicting part expansion or shrinkage, such as based on physical models of expansion or contraction for the materials simulated by the simulation.
In embodiments, the models trained by the machine learning system are utilized by the artificial intelligence system to execute simulations on the part twin for predicting part warpage.
In embodiments, the models trained by the machine learning system are utilized by the artificial intelligence system to execute simulations on the part twin for calculating necessary changes to the additive manufacturing process to compensate for part shrinkage and warpage, such as material selection, shape selection, interface selection, heat management element selection or configuration, or the like.
In embodiments, the models trained by the machine learning system and/or other AI system may undertake simulations and generate or facilitate decisions or instructions based at least in part on anticipated conditions of use, such as based on geolocation of a customer, specification for indoor or outdoor use, a set of weather and/or climate models, or the like. For example, additive manufacturing of a part that has the same intended use may be configured to use different materials, structural elements, or other elements based on whether the part is intended for use outdoors in a very cold climate, versus being used indoors or in a very hot environment. Thus, methods and systems are provided for point-of-usage aware, environment-of-usage aware, and customer type-of-usage aware automated configuration of manufacturing instructions for a part or product that involves automated manufacturing entities, such as additive manufacturing entities.
In embodiments, the models trained by the machine learning system are utilized by the artificial intelligence system to execute simulations on the part twin for testing the compatibility of 3D printed parts with other parts, with a system in which the parts will be used, with infrastructure elements of an environment of use, with ambient conditions of an environment, with available tools, and/or with a 3D printer or other additive or other manufacturing system that may be available to produce the part.
<div id="
CLAIMS
Claims ( 35 )
The invention claimed is:
1. A method of configuring a robot of a fleet of robots for use of an AI chipset, the method comprising:
receiving a request for a robotic fleet to perform a job;
defining a set of tasks that are to be performed by the robotic fleet in performance of the job;
assigning at least one task of the set of tasks to a robot;
determining a configuration for the robot based on:
the assigned task, and
a components inventory that indicates:
different components that can be provisioned to the robot, including at least one AI chipset, and
for each component:
a respective set of extended capabilities corresponding to the component, and
a respective status of the component;
configuring the robot based on the determined configuration to use the at least one AI chipset; and
deploying the robotic fleet to perform the job,
wherein a control module interface of the robot is configured to interface with the at least one AI chipset.
2. The method of claim 1 , wherein the at least one AI chipset enables the robot to perform artificial intelligence-based tasks.
3. The method of claim 1 , wherein a processing system of the at least one AI chipset is distributed amongst a team robots configured with at least one AI chipset.
4. A method of configuring a robot of a fleet of robots for use of an AI chipset, the method comprising:
receiving a request for a robotic fleet to perform a job;
defining a set of tasks that are to be performed by the robotic fleet in performance of the job;
assigning at least one task of the set of tasks to a robot;
determining a configuration for the robot based on:
the assigned task, and
a components inventory that indicates:
different components that can be provisioned to the robot, including at least one AI chipset, and
for each component:
a respective set of extended capabilities corresponding to the component, and
a respective status of the component;
configuring the robot based on the determined configuration to use the at least one AI chipset; and
deploying the robotic fleet to perform the job,
wherein a security system of each respective robot interfaces with the at least one AI chipset.
5. The method of claim 4 , wherein the at least one AI chipset performs security-related functions including autonomous adaptive and non-adaptive security functions.
6. The method of claim 4 , wherein a fleet communication management system establishes dynamic communication management functions among AI chipsets of each respective robot to enrich fleet security capabilities thereby reducing a likelihood of a successful intrusion into a fleet communication system.
7. The method of claim 4 , wherein the at least one AI chipset detects local environments with increased risk of intrusion.
8. The method of claim 4 , wherein the at least one AI chipset detects a security threat based on contextual and historical information for a robot-local environment.
9. The method of claim 4 , wherein the at least one AI chipset adapts fleet communication resources of a corresponding robot for reducing a risk associated with a detected security threat.
10. A method of configuring a robot of a fleet of robots for use of an AI chipset, the method comprising:
receiving a request for a robotic fleet to perform a job;
defining a set of tasks that are to be performed by the robotic fleet in performance of the job;
assigning at least one task of the set of tasks to a robot;
determining a configuration for the robot based on:
the assigned task, and
a components inventory that indicates:
different components that can be provisioned to the robot, including at least one AI chipset, and
for each component:
a respective set of extended capabilities corresponding to the component, and
a respective status of the component;
configuring the robot based on the determined configuration to use the at least one AI chipset; and
deploying the robotic fleet to perform the job,
wherein the at least one AI chipset enables the robot to perform artificial intelligence-based tasks.
11. A method of configuring a robot of a fleet of robots for use of an AI chipset, the method comprising:
receiving a request for a robotic fleet to perform a job;
defining a set of tasks that are to be performed by the robotic fleet in performance of the job;
assigning at least one task of the set of tasks to a robot;
determining a configuration for the robot based on:
the assigned task, and
a components inventory that indicates:
different components that can be provisioned to the robot, including at least one AI chipset, and
for each component:
a respective set of extended capabilities corresponding to the component, and
a respective status of the component;
configuring the robot based on the determined configuration to use the at least one AI chipset; and
deploying the robotic fleet to perform the job,
wherein a processing system of the at least one AI chipset is distributed amongst a team robots configured with at least one AI chipset.
12. The method of claim 11 , wherein the at least one AI chipset is configurable.
13. The method of claim 10 , wherein a control module interface of the robot is configured to interface with the at least one AI chipset.
14. The method of claim 10 , wherein a processing system of the at least one AI chipset is distributed amongst a team robots configured with at least one AI chipset.
15. A method of configuring a robot of a fleet of robots for use of an AI chipset, the method comprising:
receiving a request for a robotic fleet to perform a job;
defining a set of tasks that are to be performed by the robotic fleet in performance of the job;
assigning at least one task of the set of tasks to a robot;
determining a configuration for the robot based on:
the assigned task, and
a components inventory that indicates:
different components that can be provisioned to the robot, including at least one AI chipset, and
for each component:
a respective set of extended capabilities corresponding to the component, and
a respective status of the component;
configuring the robot based on the determined configuration to use the at least one AI chipset; and
deploying the robotic fleet to perform the job,
wherein the at least one AI chipset performs one or more artificial intelligence functions including at least one of machine-learning, natural language processing, machine vision, or analytics.
16. The method of claim 15 , wherein a control module interface of the robot is configured to interface with the at least one AI chipset.
17. The method of claim 15 , wherein the at least one AI chipset enables the robot to perform artificial intelligence-based tasks.
18. A method of configuring a robot of a fleet of robots for use of an AI chipset, the method comprising:
receiving a request for a robotic fleet to perform a job;
defining a set of tasks that are to be performed by the robotic fleet in performance of the job;
assigning at least one task of the set of tasks to a robot;
determining a configuration for the robot based on:
the assigned task, and
a components inventory that indicates:
different components that can be provisioned to the robot, including at least one AI chipset, and
for each component:
a respective set of extended capabilities corresponding to the component, and
a respective status of the component;
configuring the robot based on the determined configuration to use the at least one AI chipset; and
deploying the robotic fleet to perform the job,
wherein the at least one AI chipset operates cooperatively with an artificial intelligence service to classify objects appearing in a field of view of the robot.
19. The method of claim 18 , wherein a control module interface of the robot is configured to interface with the at least one AI chipset.
20. The method of claim 18 , wherein the at least one AI chipset enables the robot to perform artificial intelligence-based tasks.
21. A method of configuring a robot of a fleet of robots for use of an AI chipset, the method comprising:
receiving a request for a robotic fleet to perform a job;
defining a set of tasks that are to be performed by the robotic fleet in performance of the job;
assigning at least one task of the set of tasks to a robot;
determining a configuration for the robot based on:
the assigned task, and
a components inventory that indicates:
different components that can be provisioned to the robot, including at least one AI chipset, and
for each component:
a respective set of extended capabilities corresponding to the component, and
a respective status of the component;
configuring the robot based on the determined configuration to use the at least one AI chipset; and
deploying the robotic fleet to perform the job,
wherein the at least one AI chipset of the robot predicts a compromise in a robot capability based on time-to-failure data for the robot capability.
22. The method of claim 21 , wherein a control module interface of the robot is configured to interface with the at least one AI chipset.
23. The method of claim 21 , wherein the at least one AI chipset enables the robot to perform artificial intelligence-based tasks.
24. A method of configuring a robot of a fleet of robots for use of an AI chipset, the method comprising:
receiving a request for a robotic fleet to perform a job;
defining a set of tasks that are to be performed by the robotic fleet in performance of the job;
assigning at least one task of the set of tasks to a robot;
determining a configuration for the robot based on:
the assigned task, and
a components inventory that indicates:
different components that can be provisioned to the robot, including at least one AI chipset, and
for each component:
a respective set of extended capabilities corresponding to the component, and
a respective status of the component;
configuring the robot based on the determined configuration to use the at least one AI chipset; and
deploying the robotic fleet to perform the job,
wherein a robotic sensing and analysis function of the robot uses the at least one AI chipset to evaluate an object associated with a task to which the robot is assigned.
25. The method of claim 24 , wherein the at least one AI chipset evaluates an object as a target of a robotic operation.
26. The method of claim 25 , wherein the at least one AI chipset determines one or more operations to be performed by the robot based on a result of evaluating the object.
27. A system for configuring a robot of a fleet of robots for use of an AI chipset, the system comprising:
a computer-readable storage system that stores a resources data store that maintains:
a robot inventory that indicates a plurality of robots that can be assigned to a robot fleet, and for each respective robot, a set of baseline features of the robot and a respective status of the robot; and
a components inventory that indicates:
different components that can be provisioned to one or more robots, including at least one AI chipset, and
for each component:
a respective set of extended capabilities corresponding to the component, and
a respective status of the component; and
a set of one or more processors that execute a set of computer-readable instructions, wherein the set of one or more processors collectively:
receive a request for a robotic fleet to perform a job;
define a set of tasks that are to be performed by the robotic fleet in performance of the job;
assign at least one task of the set of tasks to a robot;
determine a configuration for the robot based on the assigned task and the components inventory;
configure the robot based on the determined configuration to use the at least one AI chipset; and
deploy the robotic fleet to perform the job,
wherein a control module interface of the robot is configured to interface with the at least one AI chipset.
28. The system of claim 27 , wherein the at least one AI chipset enables the robot to perform artificial intelligence-based tasks.
29. The system of claim 27 , wherein a processing system of the at least one AI chipset is distributed amongst a team robots configured with at least one AI chipset.
30. A system for configuring a robot of a fleet of robots for use of an AI chipset, the system comprising:
a computer-readable storage system that stores a resources data store that maintains:
a robot inventory that indicates a plurality of robots that can be assigned to a robot fleet, and for each respective robot, a set of baseline features of the robot and a respective status of the robot; and
a components inventory that indicates:
different components that can be provisioned to one or more robots, including at least one AI chipset, and
for each component:
a respective set of extended capabilities corresponding to the component, and
a respective status of the component; and
a set of one or more processors that execute a set of computer-readable instructions, wherein the set of one or more processors collectively:
receive a request for a robotic fleet to perform a job;
define a set of tasks that are to be performed by the robotic fleet in performance of the job;
assign at least one task of the set of tasks to a robot;
determine a configuration for the robot based on the assigned task and the components inventory;
configure the robot based on the determined configuration to use the at least one AI chipset; and
deploy the robotic fleet to perform the job,
wherein a security system of each respective robot interfaces with the at least one AI chipset.
31. The system of claim 30 , wherein the at least one AI chipset performs security-related functions including autonomous adaptive and non-adaptive security functions.
32. The system of claim 30 , wherein a fleet communication management system establishes dynamic communication management functions among AI chipsets of each respective robot to enrich fleet security capabilities thereby reducing a likelihood of a successful intrusion into a fleet communication system.
33. The system of claim 30 , wherein the at least one AI chipset detects local environments with increased risk of intrusion.
34. The system of claim 30 , wherein the at least one AI chipset detects a security threat based on contextual and historical information for a robot-local environment.
35. The system of claim 30 , wherein the at least one AI chipset adapts fleet communication resources of a corresponding robot for reducing a risk associated with a detected security threat.
US18/333,352
2020-12-18
2023-06-12
Robot fleet management configured for use of an artificial intelligence chipset
Active
US12406242B2
( en )
Priority Applications (1)
Application Number
Priority Date
Filing Date
Title
US18/333,352
US12406242B2
( en )
2020-12-18
2023-06-12
Robot fleet management configured for use of an artificial intelligence chipset
Applications Claiming Priority (8)
Application Number
Priority Date
Filing Date
Title
US202063127983P
2020-12-18
2020-12-18
US202163185348P
2021-05-06
2021-05-06
IN202111029964
2021-07-03
IN202111029964
2021-07-03
IN202111036187
2021-08-10
IN202111036187
2021-08-10
PCT/US2021/064233
WO2022133330A1
( en )
2020-12-18
2021-12-17
Robot fleet management and additive manufacturing for value chain networks
US18/333,352
US12406242B2
( en )
2020-12-18
2023-06-12
Robot fleet management configured for use of an artificial intelligence chipset
Related Parent Applications (1)
Application Number
Title
Priority Date
Filing Date
PCT/US2021/064233
Continuation
WO2022133330A1
( en )
2019-11-05
2021-12-17
Robot fleet management and additive manufacturing for value chain networks
Publications (2)
Publication Number
Publication Date
US20230341850A1
US20230341850A1 ( en )
2023-10-26
US12406242B2
true
US12406242B2 ( en )
2025-09-02
Family
ID=82058514
Family Applications (16)
Application Number
Title
Priority Date
Filing Date
US17/683,097
Granted
US20220197306A1
( en )
2020-12-18
2022-02-28
Job Parsing in Robot Fleet Resource Configuration
US17/683,145
Active
2043-03-22
US12380418B2
( en )
2020-12-18
2022-02-28
Adaptive additive manufacturing for value chain networks
US17/683,120
Active
US12333512B2
( en )
2020-12-18
2022-02-28
Robot fleet resource configuration in value chain networks
US17/683,215
Active
US12511630B2
( en )
2020-12-18
2022-02-28
Robotic vision system with variable lens for value chain networks
US17/683,198
Active
2044-05-27
US12450581B2
( en )
2020-12-18
2022-02-28
Variable focus liquid lens optical assembly for value chain networks
US17/683,173
Pending
US20220197247A1
( en )
2020-12-18
2022-02-28
Distributed Ledger for Additive Manufacturing in Value Chain Networks
US17/683,162
Abandoned
US20220197246A1
( en )
2020-12-18
2022-02-28
Digital-Twin-Assisted Additive Manufacturing for Value Chain Networks
US17/942,055
Active
US12536516B2
( en )
2020-12-18
2022-09-09
Demand-responsive robot fleet management for value chain networks
US17/942,061
Active
US12354072B2
( en )
2020-12-18
2022-09-09
AI-managed additive manufacturing for value chain networks
US17/942,065
Abandoned
US20230090334A1
( en )
2020-12-18
2022-09-09
Metal Additive Manufacturing for Value Chain Networks
US17/942,048
Active
US12541751B2
( en )
2020-12-18
2022-09-09
Robot fleet management with workflow simulation for value chain networks
US17/942,058
Active
US12361399B2
( en )
2020-12-18
2022-09-09
Distributed-ledger-based manufacturing for value chain networks
US18/333,352
Active
US12406242B2
( en )
2020-12-18
2023-06-12
Robot fleet management configured for use of an artificial intelligence chipset
US18/333,369
Active
US12561659B2
( en )
2020-12-18
2023-06-12
Machine-learned robot fleet management for value chain networks
US18/333,401
Active
US12561660B2
( en )
2020-12-18
2023-06-12
Digital-twin-enabled robot fleet management
US18/333,385
Pending
US20230342684A1
( en )
2020-12-18
2023-06-12
Distributed Ledger Tracking of Robot Fleet Task Completion
Family Applications Before (12)
Application Number
Title
Priority Date
Filing Date
US17/683,097
Granted
US20220197306A1
( en )
2020-12-18
2022-02-28
Job Parsing in Robot Fleet Resource Configuration
US17/683,145
Active
2043-03-22
US12380418B2
( en )
2020-12-18
2022-02-28
Adaptive additive manufacturing for value chain networks
US17/683,120
Active
US12333512B2
( en )
2020-12-18
2022-02-28
Robot fleet resource configuration in value chain networks
US17/683,215
Active
US12511630B2
( en )
2020-12-18
2022-02-28
Robotic vision system with variable lens for value chain networks
US17/683,198
Active
2044-05-27
US12450581B2
( en )
2020-12-18
2022-02-28
Variable focus liquid lens optical assembly for value chain networks
US17/683,173
Pending
US20220197247A1
( en )
2020-12-18
2022-02-28
Distributed Ledger for Additive Manufacturing in Value Chain Networks
US17/683,162
Abandoned
US20220197246A1
( en )
2020-12-18
2022-02-28
Digital-Twin-Assisted Additive Manufacturing for Value Chain Networks
US17/942,055
Active
US12536516B2
( en )
2020-12-18
2022-09-09
Demand-responsive robot fleet management for value chain networks
US17/942,061
Active
US12354072B2
( en )
2020-12-18
2022-09-09
AI-managed additive manufacturing for value chain networks
US17/942,065
Abandoned
US20230090334A1
( en )
2020-12-18
2022-09-09
Metal Additive Manufacturing for Value Chain Networks
US17/942,048
Active
US12541751B2
( en )
2020-12-18
2022-09-09
Robot fleet management with workflow simulation for value chain networks
US17/942,058
Active
US12361399B2
( en )
2020-12-18
2022-09-09
Distributed-ledger-based manufacturing for value chain networks
Family Applications After (3)
Application Number
Title
Priority Date
Filing Date
US18/333,369
Active
US12561659B2
( en )
2020-12-18
2023-06-12
Machine-learned robot fleet management for value chain networks
US18/333,401
Active
US12561660B2
( en )
2020-12-18
2023-06-12
Digital-twin-enabled robot fleet management
US18/333,385
Pending
US20230342684A1
( en )
2020-12-18
2023-06-12
Distributed Ledger Tracking of Robot Fleet Task Completion
Country Status (6)
Country
Link
US
( 16 )
US20220197306A1
( en )
EP
( 1 )
EP4264518A4
( en )
JP
( 1 )
JP7838763B2
( en )
KR
( 1 )
KR20230135069A
( en )
AU
( 1 )
AU2021401816A1
( en )
WO
( 1 )
WO2022133330A1
( en )
Cited By (2)
* Cited by examiner, â Cited by third party
Publication number
Priority date
Publication date
Assignee
Title
US20210194916A1
( en )
*
2019-12-24
2021-06-24
Infinite Group, Inc.
Methods for inventorying network hosts and devices thereof
US20250390571A1
( en )
*
2024-06-21
2025-12-25
Bank Of America Corporation
System and Method for Securing Software Application Based Microservices Architectures
Families Citing this family (445)
* Cited by examiner, â Cited by third party
Publication number
Priority date
Publication date
Assignee
Title
US9521040B2
( en )
*
2013-04-03
2016-12-13
Salesforce.Com, Inc.
System and method for generic configuration management system application programming interface
US12623286B2
( en )
*
2013-06-23
2026-05-12
Robert A. Flitsch
Methods and apparatus for mobile additive manufacturing of advanced roadway systems
US10789650B1
( en )
*
2016-04-27
2020-09-29
State Farm Mutual Automobile Insurance Company
Systems and methods for reconstruction of a vehicular crash
US11615285B2
( en )
2017-01-06
2023-03-28
Ecole Polytechnique Federale De Lausanne (Epfl)
Generating and identifying functional subnetworks within structural networks
US12474889B1
( en )
*
2017-04-13
2025-11-18
Electric Mirror, Llc
Apparatuses and methods for an interactive device
US11861511B2
( en )
2017-10-04
2024-01-02
Trustees Of Tufts College
Systems and methods for ensuring safe, norm-conforming and ethical behavior of intelligent systems
US12586023B2
( en )
*
2017-10-06
2026-03-24
Schlumberger Technology Corporation
Dynamic balancing of well construction and well operations planning and rig equipment total cost of ownership
EP3488977A1
( en )
2017-11-23
2019-05-29
HILTI Aktiengesellschaft
Self-aligning tool guide
EP3488974A1
( en )
*
2017-11-23
2019-05-29
HILTI Aktiengesellschaft
Self-aligning tool guide
GB2569335B
( en )
*
2017-12-13
2022-07-27
Sage Global Services Ltd
Chatbot system
US12462122B2
( en )
*
2017-12-30
2025-11-04
Telescent Inc.
Automated physical network management system utilizing high-resolution RFID, optical scans, and mobile robotic actuator
US11893471B2
( en )
2018-06-11
2024-02-06
Inait Sa
Encoding and decoding information and artificial neural networks
US11663478B2
( en )
2018-06-11
2023-05-30
Inait Sa
Characterizing activity in a recurrent artificial neural network
US12412072B2
( en )
2018-06-11
2025-09-09
Inait Sa
Characterizing activity in a recurrent artificial neural network
US11972343B2
( en )
2018-06-11
2024-04-30
Inait Sa
Encoding and decoding information
US11307584B2
( en )
2018-09-04
2022-04-19
Skydio, Inc.
Applications and skills for an autonomous unmanned aerial vehicle
US12447608B2
( en )
*
2019-01-03
2025-10-21
Lucomm Technologies, Inc.
Semantic robotic device
WO2020160778A1
( en )
*
2019-02-07
2020-08-13
Volvo Truck Corporation
Method and system for operating a fleet of vehicles
US11652603B2
( en )
2019-03-18
2023-05-16
Inait Sa
Homomorphic encryption
US11569978B2
( en )
2019-03-18
2023-01-31
Inait Sa
Encrypting and decrypting information
US20220270367A1
( en )
*
2019-03-24
2022-08-25
Dibl Co., Ltd.
Method and device for automatically recognizing sport court and determining in/out on basis of same
WO2020202316A1
( en )
*
2019-03-29
2020-10-08
ä¸è±é»æ©æ ªå¼ä¼ç¤¾
Model prediction control device, model prediction control program, model prediction control system, and model prediction control method
US11616839B2
( en )
*
2019-04-09
2023-03-28
Johnson Controls Tyco IP Holdings LLP
Intelligent edge computing platform with machine learning capability
DE102019110360A1
( en )
*
2019-04-18
2020-10-22
Volume Graphics Gmbh
Computer-implemented method for determining defects in an object manufactured using an additive manufacturing process
WO2024091861A2
( en )
*
2022-10-24
2024-05-02
Arjuna Indraeswaran Rajasingham
Air sleeper and internet network for community sourced personal protection, virtual visualization and navigation and authenticating evidence
US11579608B2
( en )
2019-08-22
2023-02-14
Walmart Apollo, Llc
System and method for removing debris from a storage facility
US12217495B2
( en )
*
2019-09-17
2025-02-04
Syntegon Technology K.K.
Learning process device and inspection device
DE102019214653A1
( en )
*
2019-09-25
2021-03-25
Rolls-Royce Deutschland Ltd & Co Kg
Training of machine learning models for data-driven decision-making
US11741305B2
( en )
*
2019-10-07
2023-08-29
The Toronto-Dominion Bank
Systems and methods for automatically assessing fault in relation to motor vehicle collisions
US11347613B2
( en )
*
2019-10-15
2022-05-31
UiPath, Inc.
Inserting probabilistic models in deterministic workflows for robotic process automation and supervisor system
AU2020379834A1
( en )
*
2019-11-05
2022-06-09
Strong Force Vcn Portfolio 2019, Llc
Control tower and enterprise management platform for value chain networks
US12572150B2
( en )
2019-11-05
2026-03-10
Strong Force Vcn Portfolio 2019, Llc
Robot fleet management for value chain networks
US20210133669A1
( en )
2019-11-05
2021-05-06
Strong Force Vcn Portfolio 2019, Llc
Control tower and enterprise management platform with robotic process automation layer to automate actions for subset of applications benefitting value chain network entities
WO2021092263A1
( en )
2019-11-05
2021-05-14
Strong Force Vcn Portfolio 2019, Llc
Control tower and enterprise management platform for value chain networks
JP7251654B2
( en )
*
2019-11-18
2023-04-04
æ¥æ¬é»æ°æ ªå¼ä¼ç¤¾
Conveying device, control method, and control program
US11651210B2
( en )
2019-12-11
2023-05-16
Inait Sa
Interpreting and improving the processing results of recurrent neural networks
US11797827B2
( en )
*
2019-12-11
2023-10-24
Inait Sa
Input into a neural network
US11580401B2
( en )
2019-12-11
2023-02-14
Inait Sa
Distance metrics and clustering in recurrent neural networks
US11816553B2
( en )
2019-12-11
2023-11-14
Inait Sa
Output from a recurrent neural network
US12282875B2
( en )
*
2019-12-30
2025-04-22
Nb Ventures, Inc.
Linkedchain, control tower and blockchain for enterprise applications
WO2021166973A1
( en )
*
2020-02-19
2021-08-26
ãã¡ããã¯æ ªå¼ä¼ç¤¾
Operation system for industrial machinery
US20210303427A1
( en )
*
2020-03-26
2021-09-30
Rohde & Schwarz Gmbh & Co. Kg
System for testing a blockchain enabled device-under-test
JP7460415B2
( en )
*
2020-03-26
2024-04-02
æ ªå¼ä¼ç¤¾ã¿ãã
Guide display system and cranes equipped with it
US11620830B2
( en )
*
2020-03-31
2023-04-04
Ford Global Technologies, Llc
Context dependent transfer learning adaptation to achieve fast performance in inference and update
US11616790B2
( en )
2020-04-15
2023-03-28
Crowdstrike, Inc.
Distributed digital security system
US11563756B2
( en )
*
2020-04-15
2023-01-24
Crowdstrike, Inc.
Distributed digital security system
US11645397B2
( en )
2020-04-15
2023-05-09
Crowd Strike, Inc.
Distributed digital security system
US11711379B2
( en )
2020-04-15
2023-07-25
Crowdstrike, Inc.
Distributed digital security system
US11189106B2
( en )
*
2020-04-27
2021-11-30
At&T Intellectual Property I, L.P.
Systems and methods for spatial remodeling in extended reality
US11580220B2
( en )
*
2020-04-30
2023-02-14
Mcafee, Llc
Methods and apparatus for unknown sample classification using agglomerative clustering
US20230214727A1
( en )
*
2020-06-05
2023-07-06
Nippon Telegraph And Telephone Corporation
Degradation Estimation Device and Degradation Estimation Method
US12321876B2
( en )
2020-07-21
2025-06-03
UiPath, Inc.
Artificial intelligence / machine learning model drift detection and correction for robotic process automation
WO2022072081A1
( en )
*
2020-09-30
2022-04-07
Arris Enterprises Llc
Infrastructure monitoring system
US11800258B2
( en )
*
2020-10-19
2023-10-24
University Of Florida Research Foundation, Incorporated
High-performance CNN inference model at the pixel-parallel CMOS image sensor
US11904538B2
( en )
*
2020-11-27
2024-02-20
The Boeing Company
Systems and methods for simultaneously manufacturing a plurality of objects
US12585231B2
( en )
2020-12-18
2026-03-24
Strong Force Vcn Portfolio 2019, Llc
Digital-twin-enabled artificial intelligence system for distributed additive manufacturing
US20230109096A1
( en )
*
2020-12-18
2023-04-06
Strong Force Vcn Portfolio 2019, Llc
Maintenance Prediction and Health Monitoring for Robotic Fleet Management
EP4264518A4
( en )
2020-12-18
2024-12-11
Strong Force VCN Portfolio 2019, LLC
ROBOT FLEET MANAGEMENT AND ADDITIVE MANUFACTURING FOR VALUE CHAIN NETWORKS
US12393915B2
( en )
2020-12-18
2025-08-19
Strong Force Vcn Portfolio 2019, Llc
Variable-focus dynamic vision for robotic system
US12202148B2
( en )
*
2020-12-22
2025-01-21
Intel Corporation
Autonomous machine collaboration
US12387145B2
( en )
*
2020-12-31
2025-08-12
The Toronto-Dominion Bank
Prediction of future occurrences of events using adaptively trained artificial-intelligence processes and contextual data
US11743350B2
( en )
2021-01-07
2023-08-29
The Toronto-Dominion Bank
System and method for integrating external services into process workflow environments
US11449312B2
( en )
*
2021-01-07
2022-09-20
The Toronto-Dominion Bank
System and method for executing a process workflow
US11928626B2
( en )
2021-01-07
2024-03-12
The Toronto-Dominion Bank