Robust Motion Planning using Markov Decision Processes and Quadtree Decomposition.
Julien BurletOlivier AycardThierry FraichardPublished in: ICRA (2004)
Keyphrases
- markov decision processes
- motion planning
- quadtree decomposition
- degrees of freedom
- state space
- path planning
- finite state
- optimal policy
- transition matrices
- policy iteration
- dynamic programming
- mobile robot
- multi robot
- reinforcement learning
- decision theoretic planning
- humanoid robot
- partially observable
- infinite horizon
- planning under uncertainty
- markov decision process
- average reward
- average cost
- reward function
- action space
- computer vision
- climbing robot
- long run
- dynamic environments
- image quality
- face recognition