Safe Reinforcement Learning for a Robot Being Pursued but with Objectives Covering More Than Capture-avoidance.
Huanhui CaoZhiyuan CaiHairuo WeiWenjie LuLin ZhangHao XiongPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- mobile robot
- real robot
- robot control
- perceptual aliasing
- autonomous learning
- robotic systems
- function approximation
- model free
- human robot interaction
- real time
- state space
- vision system
- path planning
- markov decision processes
- multiple objectives
- robot navigation
- machine learning
- transfer learning
- robot behavior
- robot manipulators
- robotic control
- reinforcement learning algorithms
- temporal difference
- goal directed
- position and orientation
- autonomous robots
- humanoid robot
- dynamic environments
- learning process
- multi agent
- obstacle avoidance
- human robot
- sensory motor
- formation control