The running control of humanoid robot utilizing Q-learning and output zeroing.
Kohei SusekiShigeki NakauraMitsuji SampeiPublished in: CDC (2007)
Keyphrases
- humanoid robot
- motion planning
- multi modal
- reinforcement learning
- legged locomotion
- human robot interaction
- joint space
- biologically inspired
- learning algorithm
- human robot
- function approximation
- fully autonomous
- pattern generator
- control problems
- control system
- motion capture
- optimal control
- state space
- action selection
- body movements
- robotic arm
- multi agent
- manipulation tasks
- mobile robot
- reinforcement learning algorithms
- vision system
- imitation learning
- computer vision
- real time
- human body