Intention Communication and Hypothesis Likelihood in Game-Theoretic Motion Planning

IEEE Robotics and Automation Letters(2023)

引用 1|浏览94
暂无评分
摘要
Game-theoretic motion planners are a potent solution for controlling systems of multiple highly interactive robots. Most existing game-theoretic planners unrealistically assume a priori objective function knowledge is available to all agents. To address this, we propose a fault-tolerant receding horizon game-theoretic motion planner that leverages inter-agent communication with intention hypothesis likelihood. Specifically, robots communicate their objective function which incorporates their intentions. A discrete Bayesian filter is designed to infer the objectives in real-time based on the discrepancy between observed trajectories and predicted solutions to non-cooperative games under available hypotheses. In simulation, we consider three safety-critical autonomous driving scenarios of overtaking, lane-merging and intersection crossing, to demonstrate our planner's ability to capitalize on alternative intention hypotheses to generate safe trajectories in the presence of faulty transmissions in the communication network.
更多
查看译文
关键词
Path planning for multiple mobile robots or agents,planning under uncertainty,collision avoidance
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要