PathRL: An End-to-End Path Generation Method for Collision Avoidance via Deep Reinforcement Learning.
Wenhao YuJie PengQuecheng QiuHanyu WangLu ZhangJianmin JiPublished in: CoRR (2023)
Keyphrases
- end to end
- collision avoidance
- generation method
- reinforcement learning
- collision free
- path finding
- path planning
- mobile robot
- optimal path
- visual navigation
- admission control
- dynamic environments
- wireless ad hoc networks
- congestion control
- shortest path
- fuzzy neural network
- multipath
- learning algorithm
- formation control
- state space
- dynamic programming
- ad hoc networks
- application layer
- rate allocation
- internet protocol
- path selection
- heuristic search
- evolutionary algorithm