An optimal control approach for exploratory actions in active tactile object recognition.
Daisuke TanakaTakamitsu MatsubaraKenji SugimotoPublished in: Humanoids (2014)
Keyphrases
- optimal control
- object recognition
- control problems
- dynamic programming
- feedback control
- risk sensitive
- control strategy
- infinite horizon
- class of nonlinear systems
- optimal control problems
- computer vision
- brownian motion
- reinforcement learning
- natural images
- real time
- decision theoretic
- average cost
- partially observable
- action selection
- control law
- data mining