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

2022/07/02 by Huanhui Cao, Zhiyuan Cai, Cao, Huanhui +9
Computer Science · Energy · Engineering · #Reinforcement Learning in Robotics #Energy, Environment, and Transportation Policies #Traffic control and management

paper · pdf · doi:10.48550/arxiv.2207.00842

Abstract

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.

Related

• A Review of Safe Reinforcement Learning: Methods, Theory and Applications
• A Dynamic Safety Shield for Safe and Efficient Reinforcement Learning of Navigation Tasks
• Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learning
• Guided by Guardrails: Control Barrier Functions as Safety Instructors for Robotic Learning
• Safe Reinforcement Learning of Robot Trajectories in the Presence of Moving Obstacles