Robot Navigation in a Crowd by Integrating Deep Reinforcement Learning and Online Planning.
Zhiqian ZhouPengming ZhuZhiwen ZengJunhao XiaoHuimin LuZongtan ZhouPublished in: CoRR (2021)
Keyphrases
- robot navigation
- reinforcement learning
- continuous state
- initially unknown
- autonomous robots
- autonomous mobile robot
- real time stereo
- map building
- real time
- action selection
- scene understanding
- function approximation
- landmark recognition
- state space
- model free
- planning problems
- topological map
- motion planning
- temporal difference
- belief state
- partially observable
- markov decision processes
- object detection
- dynamic programming
- high resolution
- object recognition