Rajeev Yasarla, Deepti Hegde, Hsin-Pai Cheng, Shizhong Han, Yunxiao Shi, Meysam Sadeghigooghari, Hanno Ackermann, Litian Liu, Pranav Desai, Fatih Porikli, Mohammad Ghavamzadeh, Hong Cai
Vision-language-action (VLA) models are effective as end-to-end motion planners, but can be brittle when evaluated in closed-loop settings due to being trained under traditional imitation learning framework. Existing closed-loop supervision approaches lack scalability and fail to completely model a reactive environment. We propose MAPLE, a novel framework for reactive, multi-agent rollout of a dynamic driving scenario in the latent space of the VLA model. The ego vehicle and nearby traffic agents are independently controlled over multi-step horizons, while being reactive to other agents in the scene, enabling closed-loop training. MAPLE consists of two training stages: (1) supervised fine-tuning on the latent rollouts based on ground-truth trajectories, followed by (2) reinforcement learning with global and agent -specific rewards that encourage safety, progress, and interaction realism. We further propose diversity rewards that encourage the model to generate planning behaviors that may not be present in logged driving data. Notably, our closed-loop training framework is scalable and does not require external simulators, which can be computationally expensive to run and have limited visual fidelity to the real-world. MAPLE achieves state-of-the-art driving performance on Bench2Drive and demonstrates scalable, closed-loop multi-agent play for robust E2E autonomous driving systems.
Delving into Mapping Uncertainty for Mapless Trajectory Prediction
Institute for AI Industry Research (AIR), Tsinghua University, China(人工智能产业研究院(AIR),清华大学,中国);Bosch Corporate Research, China(博世企业研究,中国);Institute for Interdisciplinary Information Sciences(IIIS), Tsinghua University, China(交叉信息学研究院(IIIS),清华大学,中国);University of Toronto, Canada(多伦多大学,加拿大);University of HongKong, China(香港大学,中国)
针对无地图自动驾驶中在线建图可靠性问题,本文提出本体感知场景门控与基于协方差的地图不确定性方法,在 nuScenes 上较 SOTA 最高提升23.6%。
A Framework for a Capability-driven Evaluation of Scenario Understanding for Multimodal Large Language Models in Autonomous Driving
Dr. Ing. h.c. F. Porsche AG(保时捷股份公司);Forschungszentrum Informatik(弗劳恩霍夫信息技术研究中心);Hochschule Esslingen(埃斯林根应用技术大学);University of Michigan(密歇根大学);Voxel51;Karlsruher Institut für Technologie(卡尔斯鲁厄理工学院)
CoLMIN: LLM-based Multi-Decision Path Negotiation for Cooperative Autonomous Driving
School of future Transportation, Chang’an University(长安大学未来交通学院);Hangzhou International Innovation Institute, Beihang University(北京航空航天大学杭州国际创新研究院);School of information, Renmin University of China(中国人民大学信息学院);School of Artificial Intelligence and Robotics, Hunan University(湖南大学人工智能与机器人学院)
Data-Centric Evolution in Autonomous Driving: A Comprehensive Survey of Big Data System, Data Mining, and Closed-Loop Technologies
University of New South Wales(新南威尔士大学);CSIRO(澳大利亚联邦科学与工业研究组织);BYD(比亚迪);University of Notre Dame(圣母大学);The University of Sydney(悉尼大学);South China University of Technology(华南理工大学)
Machine Learning-Based Vehicle Intention Trajectory Recognition and Prediction for Autonomous Driving
University of Southern California(南加州大学);Virginia Tech(弗吉尼亚理工大学);Miami University(迈阿密大学);Northern Arizona University(北亚利桑那大学);Northeastern University(东北大学)
Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);East China Normal University(华东师范大学);Chinese University of Hong Kong(香港中文大学);Zhejiang University(浙江大学)
Deep Neural Network Perception Models and Robust Autonomous Driving Systems
Waterloo Artificial Intelligence Institute(滑铁卢人工智能研究所);Department of Systems Design Engineering, University of Waterloo(滑铁卢大学系统设计工程系);David Cheriton school of Computer science, University of Waterloo(滑铁卢大学戴维·谢里顿计算机学院);University of Waterloo(滑铁卢大学)
Motion Comfort Optimization for Autonomous Vehicles: Concepts, Methods, and Techniques
University of North Texas(北德克萨斯大学);Fordham University(福特汉姆大学);Qatar University(卡塔尔大学);University of Nebraska at Kearney(内布拉斯加大学卡尼尔分校);Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI)(穆罕默德·本·扎耶德人工智能大学(MBZUAI));Hamad Bin Khalifa University(哈马德·本·哈利法大学)