Decentralized Swarm Collision Avoidance for Quadrotors via End-to-End Reinforcement Learning.
Ramzi OurariKai CuiHeinz KoepplPublished in: CoRR (2021)
Keyphrases
- end to end
- collision avoidance
- reinforcement learning
- formation control
- decentralized control
- path planning
- mobile robot
- visual navigation
- dynamic environments
- markov decision processes
- particle swarm optimization
- admission control
- real robot
- optimal policy
- state space
- fuzzy neural network
- path finding
- multi robot systems
- congestion control
- dynamic programming
- learning algorithm
- scalable video
- smart grid
- peer to peer
- search space
- application layer
- control policy
- search algorithm