Safe multi-agent motion planning under uncertainty for drones using filtered reinforcement learning.
Sleiman SafaouiAbraham P. VinodAnkush ChakrabartyRien QuirynenNobuyuki YoshikawaStefano Di CairanoPublished in: CoRR (2023)
Keyphrases
- planning under uncertainty
- multi agent
- reinforcement learning
- robotic tasks
- markov decision processes
- partially observable markov decision processes
- decision theoretic
- belief space
- ai planning
- multi agent systems
- decision theoretic planning
- optimal policy
- image sequences
- multiple agents
- dynamical systems
- human motion
- moving objects
- state space
- learning algorithm
- single agent
- finite state
- machine learning
- dynamic programming
- motion planning
- special case
- search algorithm