用强化学习让自动驾驶赛车可靠超车，实测成功率87%。
Accelerating Real-World Overtaking in F1TENTH Racing Employing Reinforcement Learning Methods
- 训练智能体对抗对手，学会主动超车
- 真实赛道超车成功率87%，远超仅竞速训练的56%
- 适用于需复杂交互的自动驾驶竞赛场景
尽管自动竞速在计时赛中已取得显著进展，但真实的车对车竞速与超车能力仍严重受限。这些局限在现实驾驶中尤为明显，当前先进算法难以安全可靠地完成超车动作。而可靠绕行其他车辆对自动驾驶车对车竞速至关重要。F1Tenth竞赛为在标准化物理平台上开发车对车竞速算法提供了良机，其赛制可评估超车与竞速算法的性能。本研究提出一种新型竞速与超车智能体，能在仿真和真实环境中可靠地导航并超车对手。该智能体部署于实际F1Tenth车辆，并与运行不同竞争算法的对手在现实中对战。结果表明，针对对手训练使智能体展现出有意识的超车行为，超车成功率达87%，而仅训练竞速的智能体仅为56%。
原文摘要 · Abstract (English)
While autonomous racing performance in Time-Trial scenarios has seen significant progress and development, autonomous wheel-to-wheel racing and overtaking are still severely limited. These limitations are particularly apparent in real-life driving scenarios where state-of-the-art algorithms struggle to safely or reliably complete overtaking manoeuvres. This is important, as reliable navigation around other vehicles is vital for safe autonomous wheel-to-wheel racing. The F1Tenth Competition provides a useful opportunity for developing wheel-to-wheel racing algorithms on a standardised physical platform. The competition format makes it possible to evaluate overtaking and wheel-to-wheel racing algorithms against the state-of-the-art. This research presents a novel racing and overtaking agent capable of learning to reliably navigate a track and overtake opponents in both simulation and reality. The agent was deployed on an F1Tenth vehicle and competed against opponents running varying competitive algorithms in the real world. The results demonstrate that the agent's training against opponents enables deliberate overtaking behaviours with an overtaking rate of 87% compared 56% for an agent trained just to race.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。