Reinforcement Learned Distributed Multi-Robot Navigation with Reciprocal Velocity Obstacle Shaped Rewards.
Ruihua HanShengduo ChenShuaijun WangZeqing ZhangRui GaoQi HaoJia PanPublished in: CoRR (2022)
Keyphrases
- robot navigation
- reinforcement learning
- autonomous mobile robot
- autonomous robots
- distributed systems
- mobile robot
- map building
- landmark recognition
- multi agent
- real time stereo
- markov decision processes
- robot localization
- scene understanding
- kalman filter
- topological map
- velocity field
- real time
- pairwise
- object recognition
- support vector
- high quality