LiloDriver: A Lifelong Learning Framework for Closed-loop Motion Planning in Long-tail Autonomous Driving Scenarios

[2505.17209] LiloDriver: A Lifelong Learning Framework for Closed-loop Motion Planning in Long-tail Autonomous Driving Scenarios Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Robotics arXiv:2505.17209 (cs) [Submitted on 22 May 2025 ( v1 ), last revised 9 Apr 2026 (this version, v2)] Title: LiloDriver: A Lifelong Learning Framework for Closed-loop Motion Planning in Long-tail Autonomous Driving Scenarios Authors: Huaiyuan Yao , Pengfei Li , Bu Jin , Yupeng Zheng , An Liu , Lisen Mu , Qing Su , Qian Zhang , Yilun Chen , Peng Li View a PDF of the paper titled LiloDriver: A Lifelong Learning Framework for Closed-loop Motion Planning in Long-tail Autonomous Driving Scenarios, by Huaiyuan Yao and 9 other authors View PDF HTML (experimental) Abstract: Recent advances in autonomous driving research towards motion planners that are robust, safe, and adaptive. However, existing rule-based and data-driven planners lack adaptability to long-tail scenarios, while knowledge-driven methods offer strong reasoning but face challenges in representation, control, and real-world evaluation. To address these challenges, we present LiloDriver, a lifelong learning framework for closed-loop motion planning in long-tail autonomous driving scenarios. By integrating large language models (LLMs) with a memory-augmented planner generation system, LiloDriver continuously adapts to new scenarios without retraining. It features a four-stage architecture including perception, scene encoding, memory-based strategy refinement, and LLM-guided reasoning. Evaluated on the nuPlan benchmark, LiloDriver achieves superior performance in both common and rare driving scenarios, outperforming static rule-based and learning-based planners. Our results highlight the effectiveness of combining structured memory and LLM reasoning to enable scalable, human-like motion planning in real-world autonomous driving. Our code is available at this https URL . Comments: 7 pages, 3 figures Subjects: Robotics (cs.RO) ; Artificial Intelligence (cs.AI) MSC classes: 68T05 ACM classes: I.2.9; I.2.7; I.2.6 Cite as: arXiv:2505.17209 [cs.RO] (or arXiv:2505.17209v2 [cs.RO] for this version) https://doi.org/10.48550/arXiv.2505.17209 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Huaiyuan Yao [ view email ] [v1] Thu, 22 May 2025 18:33:08 UTC (551 KB) [v2] Thu, 9 Apr 2026 11:34:12 UTC (554 KB) Full-text links: Access Paper: View a PDF of the paper titled LiloDriver: A Lifelong Learning Framework for Closed-loop Motion Planning in Long-tail Autonomous Driving Scenarios, by Huaiyuan Yao and 9 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.RO < prev | next > new | recent | 2025-05 Change to browse by: cs cs.AI References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• In Two Minds about Lifelong Learning: Exploring Hemispheric Redundancy and Specialisation in Neural Models#1117554
• Enhanced SIRRT*: A Structure-Aware RRT* for 2D Path Planning with Hybrid Smoothing and Bidirectional Rewiring#1142539
• Long-Horizon Consistent and Interaction-Aware World Models for Multi-Style End-to-End Driving#925582
• Can We Get There Faster: Tuning Sample-based Path Planners#176207
• A unified deep learning framework integrating OpenStreetMap for multi-domain urban planning tasks#5854