Indoor Pursuit-Evasion with Hybrid Hierarchical Partially Observable Markov Decision Processes for Multi-robot Systems.
Sha YiChangjoo NamKatia P. SycaraPublished in: DARS (2018)
Keyphrases
- multi robot systems
- pursuit evasion
- partially observable markov decision processes
- multi agent
- multi robot
- finite state
- belief space
- belief state
- partially observable stochastic games
- dynamical systems
- reinforcement learning
- optimal policy
- multiple robots
- mobile robot
- dynamic programming
- decision problems
- autonomous robots
- state space
- planning problems
- markov decision processes
- partially observable markov
- indoor environments
- dynamic environments
- markov chain
- machine learning
- robot navigation
- approximate solutions