Planning to see: A hierarchical approach to planning visual actions on a robot using POMDPs.
Mohan SridharanJeremy L. WyattRichard DeardenPublished in: Artif. Intell. (2010)
Keyphrases
- stochastic domains
- motion planning
- partially observable
- decision theoretic
- goal directed
- action selection
- planning problems
- belief space
- world model
- plan recognition
- state space
- macro actions
- reinforcement learning
- goal state
- planning process
- path planning
- partially observable markov decision processes
- predictive state representations
- decision theoretic planning
- external events
- multiple agents
- initial state
- visual information
- heuristic search
- vision system
- mobile robot
- search space