期刊
IEEE ROBOTICS AND AUTOMATION LETTERS
卷 6, 期 3, 页码 4257-4264出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/LRA.2021.3064284
关键词
Autonomous agents; reinforcement learning
类别
资金
- Sony R&D Center Europe Stuttgart Laboratory 1
- National Centre of Competence in Research (NCCR) Robotics through the Swiss National Science Foundation
- SNSF-ERC Starting Grant
Autonomous car racing presents a major challenge in robotics, but a learning-based system using high-fidelity car simulation, proxy rewards, and deep reinforcement learning has shown impressive performance, surpassing human players and built-in AI in Gran Turismo Sport.
Autonomous car racing is a major challenge in robotics. It raises fundamental problems for classical approaches such as planning minimum-time trajectories under uncertain dynamics and controlling the car at the limits of its handling. Besides, the requirement of minimizing the lap time, which is a sparse objective, and the difficulty of collecting training data from human experts have also hindered researchers from directly applying learning-based approaches to solve the problem. In the present work, we propose a learning-based system for autonomous car racing by leveraging a high-fidelity physical car simulation, a course-progress proxy reward, and deep reinforcement learning. We deploy our system in Gran Turismo Sport, a world-leading car simulator known for its realistic physics simulation of different race cars and tracks, which is even used to recruit human race car drivers. Our trained policy achieves autonomous racing performance that goes beyond what had been achieved so far by the built-in AI, and at the same time, outperforms the fastest driver in a dataset of over 50,000 human players.
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