World model based reinforcement learning (RL) has emerged as a promising approach for autonomous driving, which learns a latent dynamics model and uses it to train a planning policy. To speed up the learning process, the pretrain-finetune paradigm is often used, where online RL is initialized by a pretrained model and a policy learned offline. However, naively performing such initialization in RL may result in dramatic performance degradation during the online interactions in the new task. To tackle this challenge, we first analyze the performance degradation and identify two primary root causes therein: the mismatch of the planning policy and the mismatch of the dynamics model, due to distribution shift. We further analyze the effects of these factors on performance degradation during finetuning, and our findings reveal that the choice of finetuning strategies plays a pivotal role in mitigating these effects. We then introduce AdaWM, an Adaptive World Model based planning method, featuring two key steps: (a) mismatch identification, which quantifies the mismatches and informs the finetuning strategy, and (b) alignment-driven finetuning, which selectively updates either the policy or the model as needed using efficient low-rank updates. Extensive experiments on the challenging CARLA driving tasks demonstrate that AdaWM significantly improves the finetuning process, resulting in more robust and efficient performance in autonomous driving systems.
HyPlan: Hybrid Learning-Assisted Planning Under Uncertainty for Safe Autonomous Driving
Saarland University, Computer Science Dept.(萨尔兰大学计算机科学系);German Research Center for Artificial Intelligence (DFKI)(德国人工智能研究中心);French National Centre for Scientific Research (CNRS)(法国国家科学研究中心)
CarPLAN: Context-Adaptive and Robust Planning with Dynamic Scene Awareness for Autonomous Driving
Department of Artificial Intelligence, Hanyang University(翰林大学人工智能系);Interdisciplinary Program in Artificial Intelligence, Seoul National University(首尔国立大学人工智能跨学科项目);Department of Electrical and Computer Engineering, Seoul National University(首尔国立大学电子与计算机工程系);Department of Automotive Engineering, Hanyang University(翰林大学汽车工程系)
AppleVLM: End-to-end Autonomous Driving with Advanced Perception and Planning-Enhanced Vision-Language Models
Shenzhen Key Lab for Advanced Motion Control and Modern Automation Equipments(深圳先进运动控制系统与现代自动化装备重点实验室);Guangdong Provincial Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics(广东省智能变形机制与适应机器人省重点实验室);School of Intelligence Science and Engineering(智能科学与工程学院);Harbin Institute of Technology(哈尔滨工业大学);National Key Laboratory of Smart Farm Technologies and Systems(国家智能农业技术与系统重点实验室);Autonomous Driving Center(自动驾驶中心);Shanghai Utopilot Technology Co.Ltd.(上海驭目科技有限公司)
Diffusion-Based Planning for Autonomous Driving with Flexible Guidance
Tsinghua University(清华大学);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);The Chinese University of Hong Kong(香港中文大学);Shanghai Jiao Tong University(上海交通大学);Shanghai Artificial Intelligence Laboratory(上海人工智能实验室)
LLM-Driven Scenario-Aware Planning for Autonomous Driving
University of Macau(澳门大学);Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences(中国科学院深圳先进技术研究所);Southern University of Science and Technology(南方科技大学)
BEVGPT: Generative Pre-trained Large Model for Autonomous Driving Prediction, Decision-Making, and Planning
The Hong Kong University of Science and Technology(香港科技大学);The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));Tongji University(同济大学);University of Washington(华盛顿大学)
Predictive Maneuver Planning with Deep Reinforcement Learning (PMP-DRL) for comfortable and safe autonomous driving
Robert Bosch Centre for Cyber-Physical Systems, Indian Institute of Science(印度科学学院罗伯特·博世信息物理系统中心);Indian Institute of Science(印度科学学院);PES university(PES大学)
An Autonomous Driving Model Integrated with BEV-V2X Perception, Fusion Prediction of Motion and Occupancy, and Driving Planning, in Complex Traffic Intersections
P4P: Conflict-Aware Motion Prediction for Planning in Autonomous Driving
Tsinghua University(清华大学);Shanghai Qi Zhi Institute(上海期智研究院);Massachusetts Institute of Technology(麻省理工学院)
运动预测对于在交互式场景中实现自动驾驶车辆的安全运动规划至关重要。它允许规划者识别与其他交通代理的潜在冲突并生成安全的计划。现有的运动预测器通常专注于减少预测误差,但它们如何帮助规划器识别冲突仍然是一个悬而未决的问题。在本文中,我们通过新的冲突相关的指标,如识别冲突的成功率,评估国家的最先进的预测。令人惊讶的是,预测遭受低成功率,从而导致很大比例的碰撞时,我们在一个交互式模拟器中测试的预测规划系统。为了填补这一空白,我们提出了一个简单但有效的替代方案,它结合了基于物理的轨迹生成器和基于学习的关系预测器来识别冲突并推断冲突关系。我们证明了我们的预测器P4P在Waymo Open Motion Dataset的现实交互式驾驶场景中比现有的基于学习的预测器具有更好的性能。
Risk Map As Middleware: Towards Interpretable Cooperative End-to-end Autonomous Driving for Risk-Aware Planning
Key Laboratory of Road and Traffic Engineering of the Ministry of Education, Tongji University(教育部道路与交通工程重点实验室,同济大学);UCLA Mobility Lab, University of California, Los Angeles(加州大学洛杉矶分校UCLA移动实验室)
FeaXDrive: Feasibility-aware Trajectory-Centric Diffusion Planning for End-to-End Autonomous Driving
College of Automotive and Energy Engineering, Tongji University(同济大学汽车与能源工程学院);College of Transportation Engineering, Tongji University(同济大学交通工程学院);School of Mechanical and Aerospace Engineering, Nanyang Technological University(南洋理工大学机械与航空航天工程学院)