Autonomous driving systems demand trajectory planners that not only model the inherent uncertainty of future motions but also respect complex temporal dependencies and underlying physical laws. While diffusion-based generative models excel at capturing multi-modal distributions, they often fail to incorporate long-term sequential contexts and domain-specific physical priors. In this work, we bridge these gaps with two key innovations. First, we introduce a Diffusion Mamba Transformer architecture that embeds mamba and attention into the diffusion process, enabling more effective aggregation of sequential input contexts from sensor streams and past motion histories. Second, we design a Port-Hamiltonian Neural Network module that seamlessly integrates energy-based physical constraints into the diffusion model, thereby enhancing trajectory predictions with both consistency and interpretability. Extensive evaluations on standard autonomous driving benchmarks demonstrate that our unified framework significantly outperforms state-of-the-art baselines in predictive accuracy, physical plausibility, and robustness, thereby advancing safe and reliable motion planning.
PIE: Perception and Interaction Enhanced End-to-End Motion Planning for Autonomous Driving
Department of Mechanical Engineering, National University of Singapore（机械工程系，国立新加坡大学）；Department of Civil and Environmental Engineering, National University of Singapore（土木与环境工程系，国立新加坡大学）
GeoDrive: 3D Geometry-Informed Driving World Model with Precise Action Control
State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University（多媒体信息处理国家重点实验室，计算机学院，北京大学）；Li Auto Inc.（利亚德公司）；UC Berkeley（加州大学伯克利分校）
Physics-informed Imitative Reinforcement Learning for Real-world Driving
Robotics and Autonomous Systems Thrust, Systems Hub, The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州）机器人与自主系统 thrust、系统枢纽）；Department of Computer Science and Engineering, School of Engineering, The Hong Kong University of Science and Technology（香港科技大学计算机科学与工程系、工程学院）
A Knowledge-Informed Deep Learning Paradigm for Generalizable and Stability-Optimized Car-Following Models
School of Advanced Technology（先进技术学院）；Institute of Transport Studies（交通研究所）；Department of Computer Science（计算机科学系）；City University of Hong Kong（香港城市大学）
Physics-informed Deep Mixture-of-Koopmans Vehicle Dynamics Model with Dual-branch Encoder for Distributed Electric-drive Trucks
School of Vehicle and Mobility, and State Key Laboratory of Intelligent Green Vehicle and Mobility, Tsinghua University, Beijing, China（车辆与移动系统学院和智能绿色车辆与移动系统国家重点实验室，清华大学，北京，中国）；KargoBot Inc., Beijing, China（KargoBot公司，北京，中国）
Knowledge-Informed Multi-Agent Trajectory Prediction at Signalized Intersections for Infrastructure-to-Everything
College of Electronic and Information Engineering, Tongji University（同济大学电子与信息工程学院）；Shanghai Institute of Intelligent Science and Technology, Tongji University（同济大学上海智能科学与技术研究院）；Department of Electrical and Computer Engineering, Technical University of Munich（慕尼黑技术大学电子与计算机工程系）
A Data-Informed Analysis of Scalable Supervision for Safety in Autonomous Vehicle Fleets
Institute for Data, Systems, and Society, Massachusetts Institute of Technology（麻省理工学院数据、系统与社会研究所）；Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology（麻省理工学院电气工程与计算机科学系）；Department of Civil and Environmental Engineering, Massachusetts Institute of Technology（麻省理工学院土木工程与环境工程系）
LANet: A Lane Boundaries-Aware Approach For Robust Trajectory Prediction
Artificial Intelligence Creative Research Lab, ETRI University of Science（ETRI人工智能创意研究实验室，科学技术大学）；Artificial Intelligence Creative Research Lab, ETRI Daejeon, South Korea（ETRI人工智能创意研究实验室，韩国大田）
TIP: Task-Informed Motion Prediction for Intelligent Vehicles
Massachusetts Institute of Technology（麻省理工学院）；Toyota Research Institute（丰田研究院）
在预测道路智能体的轨迹时，运动预测器通常通过有限数量的样本来近似未来的分布。该约束要求预测器生成最好地支持给定任务规范的任务的样本。然而，现有的预测器通常通过任务不可知的措施进行优化和评估，而不考虑在下游任务中使用预测，因此可能导致次优的任务性能。在本文中，我们提出了一个任务知情的运动预测模型，更好地支持任务，通过其预测，通过联合推理预测精度和下游任务的效用，这是常用的任务性能评估。任务效用函数不需要完整的任务信息，而是需要任务效用的规范，从而产生服务于广泛的下游任务的预测器。我们在自动驾驶和并行自动驾驶的背景下，在两个常见决策任务及其效用函数的用例上展示了我们的方法。实验结果表明，与Waymo Open Motion数据集上的任务不可知基线相比，我们的预测器可以产生准确的预测，从而大幅提高两项任务的任务性能。
VEGA: Electric Vehicle Navigation Agent via Physics-Informed Neural Operator and Proximal Policy Optimization
Department of Mechanical Engineering, State University of New York（机械工程系，纽约州立大学）；Department of Computer Science, State University of New York（计算机科学系，纽约州立大学）
Human Behavior-Informed Crash Scenario Generation with Real-World Crash Priors for Autonomous Vehicle Safety Evaluation
The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；Institute of Automation Chinese Academy of Sciences（中国科学院自动化研究所）；The University of Hong Kong（香港大学）；Shenzhen University（深圳大学）
