Autonomous off-road driving is challenging as risky actions taken by the robot may lead to catastrophic damage. As such, developing controllers in simulation is often desirable as it provides a safer and more economical alternative. However, accurately modeling robot dynamics is difficult due to the complex robot dynamics and terrain interactions in unstructured environments. Domain randomization addresses this problem by randomizing simulation dynamics parameters, however this approach sacrifices performance for robustness leading to policies that are sub-optimal for any target dynamics. We introduce a novel model-based reinforcement learning approach that aims to balance robustness with adaptability. Our approach trains a System Identification Transformer (SIT) and an Adaptive Dynamics Model (ADM) under a variety of simulated dynamics. The SIT uses attention mechanisms to distill state-transition observations from the target system into a context vector, which provides an abstraction for its target dynamics. Conditioned on this, the ADM probabilistically models the system's dynamics. Online, we use a Risk-Aware Model Predictive Path Integral controller (MPPI) to safely control the robot under its current understanding of the dynamics. We demonstrate in simulation as well as in multiple real-world environments that this approach enables safer behaviors upon initialization and becomes less conservative (i.e. faster) as its understanding of the target system dynamics improves with more observations. In particular, our approach results in an approximately 41% improvement in lap-time over the non-adaptive baseline while remaining safe across different environments.
Virtual Roads, Smarter Safety: A Digital Twin Framework for Mixed Autonomous Traffic Safety Analysis
Zachry Department of Civil and Environmental Engineering, Texas A&M University(土木与环境工程系,德克萨斯A&M大学);Department of Landscape Architecture and Urban Planning(景观建筑与城市规划系)
Harnessing Smartphone Sensors for Enhanced Road Safety: A Comprehensive Dataset and Review
Qatar University(卡塔尔大学);The University of British Columbia(不列颠哥伦比亚大学);Rajshahi University of Engineering & Technology(拉杰沙希工程技术大学);KINDI Center for Computing Research(金迪计算研究中心);Qatar Mobility Innovations Center (QMIC)(卡塔尔移动创新中心);Manchester Metropolitan University(曼彻斯特城市大学)
Impact of Level 2/3 Automated Driving Technology on Road Work Zone Safety
Faculty of Railway Transportation, Shanghai Institute of Technology(上海应用技术大学轨道交通学院);College of Computer Science and Technology, Zhejiang University(浙江大学计算机科学与技术学院)
Optimal Placement of Roadside Infrastructure Sensors towards Safer Autonomous Vehicle Deployments
Centre of Excellence for Testing & Research of AVs - NTU (CETRAN)(南洋理工大学自动驾驶车辆测试与研究卓越中心(CETRAN));Nanyang Technological University(南洋理工大学);Siemens Mobility Pte. Ltd.(西门子交通私人有限公司)
Quantification of Actual Road User Behavior on the Basis of Given Traffic Rules
FZI Research Center for Information Technology(FZI信息技术研究中心)
道路上的驾驶受到各种交通规则的限制,旨在确保所有交通参与者的安全。然而,人类道路使用者通常不严格遵守这些规则,导致不同程度的规则符合性。这种对既定规则的偏离是当今道路交通的关键组成部分。在自动驾驶中,当不考虑规则偏差时,机器人代理可能会扰乱交通流量。在本文中,我们提出了一种方法来获得的规则符合度的分布,从人类驾驶数据。我们使用Waymo Open Motion数据集和安全距离和速度限制规则来演示我们的方法。
Smart Roads: Roadside Perception, Vehicle-Road Cooperation and Business Model
Xidian University(西安电子科技大学);Guangzhou Institute of Technology, Xidian University(西安电子科技大学广州研究院);Eindhoven University of Technology(埃因霍温理工大学);Nanyang Technological University(南洋理工大学);University of Oslo(奥斯陆大学);Simula Metropolitan Center for Digital Engineering(西穆拉大都会数字工程中心)