Acquisition of a Gymnast-Like Robotic Giant-Swing Motion by Q-Learning and Improvement of the Repeatability.
Masayuki HaraNaoto KawabeJian HuangTetsuro YabutaPublished in: J. Robotics Mechatronics (2011)
Keyphrases
- reinforcement learning
- robotic tasks
- motion estimation
- image sequences
- motion analysis
- cooperative
- human motion
- optical flow
- learning algorithm
- motion model
- state space
- robot motion
- space time
- multi agent
- motion field
- function approximation
- moving objects
- motion parameters
- motion detection
- spatial and temporal
- camera motion
- feature detection
- motion capture
- dynamic programming
- connected components
- video sequences
- mobile robot
- human body
- motion tracking
- real robot
- real time