A Study of Reinforcement Learning for the Robot with Many Degrees of Freedom - Acquisition of Locomotion Patterns for Multi Legged Robot.
Kazuyuki ItoFumitoshi MatsunoPublished in: ICRA (2002)
Keyphrases
- degrees of freedom
- legged robots
- motion planning
- robotic arm
- reinforcement learning
- end effector
- mobile robot
- path planning
- configuration space
- robot control
- pose estimation
- stability margin
- learning algorithm
- real robot
- dynamic environments
- vision system
- state space
- computer vision
- robotic manipulator
- joint space
- real time