End-to-end Decentralized Multi-robot Navigation in Unknown Complex Environments via Deep Reinforcement Learning.
Juntong LinXuyun YangPeiwei ZhengHui ChengPublished in: CoRR (2019)
Keyphrases
- end to end
- robot navigation
- complex environments
- initially unknown
- reinforcement learning
- continuous state
- learning agents
- autonomous mobile robot
- sequential decision tasks
- multi agent
- autonomous robots
- wireless ad hoc networks
- landmark recognition
- autonomous agents
- machine learning
- congestion control
- cooperative
- topological map
- scene understanding
- agent learns
- internet protocol
- scalable video
- learning algorithm
- optimal policy
- real world
- markov decision processes
- text localization and recognition
- video surveillance