期刊
IEEE TRANSACTIONS ON ROBOTICS
卷 37, 期 6, 页码 2157-2172出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TRO.2021.3075376
关键词
Games; Uncertainty; Robots; Vehicle dynamics; Planning; Nash equilibrium; Approximation algorithms; Game-theoretic planning; motion and path planning; multirobot systems; optimization and optimal control
类别
资金
- Office of Naval Research (ONR) [1723943]
- Toyota Research Institute (TRI) [N00014-18-1-2830]
Gathering information while interacting with other agents in environments with sensing and motion uncertainty is critical in various domains. Agents must predict others' future actions without communication, account for uncertainty and noise in information gathering, and consider what information their actions reveal. Our algorithm, using local iterative dynamic programming in Gaussian belief space, achieves a runtime polynomial in the number of agents and linear in the planning horizon, providing linear feedback policies for our robot.
Information gathering while interacting with other agents under sensing and motion uncertainty is critical in domains such as driving, service robots, racing, or surveillance. The interests of agents may be at odds with others, resulting in a stochastic noncooperative dynamic game. Agents must predict others' future actions without communication, incorporate their actions into these predictions, account for uncertainty and noise in information gathering, and consider what information their actions reveal. Our solution uses local iterative dynamic programming in Gaussian belief space to solve a game-theoretic continuous POMDP. Solving a quadratic game in the backward pass of a game-theoretic belief-space variant of iterative linear-quadratic Gaussian control (iLQG) achieves a runtime polynomial in the number of agents and linear in the planning horizon. Our algorithm yields linear feedback policies for our robot, and predicted feedback policies for other agents. We present three applications: Active surveillance, guiding eyes for a blind agent, and autonomous racing. Agents with game-theoretic belief-space planning win 44% more races than without game theory and 34% more than without belief-space planning.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据