arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2207.00842eess.SYcs.SY
收藏

被追击但目标覆盖范围超过捕获-避免的机器人的安全强化学习

Safe Reinforcement Learning for a Robot Being Pursued but with Objectives Covering More Than Capture-avoidance

Huanhui Cao, Zhiyuan Cai, Hairuo Wei, Wenjie Lu, Lin Zhang, Hao Xiong

摘要:

近年来,强化学习(RL)算法表现出惊人的性能,但将RL应用于自动驾驶汽车等实际应用中可能会遇到安全问题。按照学习策略移动到目标位置的自动驾驶车辆可能遭受具有不可预测的攻击行为的车辆,甚至被遵循纳什策略的车辆追赶。为了解决这种情况下的自动驾驶汽车的安全问题,本文进行了初步研究的基础上,系统的机器人。一个安全的RL框架的安全保证被追求的机器人,但目标覆盖超过捕获避免。基于机器人系统进行了仿真和实验,以评估所开发的安全RL框架的有效性。

英文摘要:

Reinforcement Learning (RL) algorithms show amazing performance in recent years, but placing RL in real-world applications such as self-driven vehicles may suffer safety problems. A self-driven vehicle moving to a target position following a learned policy may suffer a vehicle with unpredictable aggressive behaviors or even being pursued by a vehicle following a Nash strategy. To address the safety issue of the self-driven vehicle in this scenario, this paper conducts a preliminary study based on a system of robots. A safe RL framework with safety guarantees is developed for a robot being pursued but with objectives covering more than capture-avoidance. Simulations and experiments are conducted based on the system of robots to evaluate the effectiveness of the developed safe RL framework.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑