Towards continuous control of flippers for a multi-terrain robot using deep reinforcement learning.
Giuseppe PaoloLei TaiMing LiuPublished in: CoRR (2017)
Keyphrases
- robot control
- reinforcement learning
- legged robots
- walking robot
- mobile robot
- rough terrain
- optimal control
- control problems
- robot behavior
- robotic systems
- visual servoing
- autonomous robots
- motion control
- robotic arm
- quadruped robot
- real robot
- hand eye
- control system
- action space
- wheeled mobile robots
- state space
- action selection
- robotic control
- vision system
- markov decision processes
- control signals
- human operators
- multi robot
- home environment
- modular robots
- dynamic programming
- robot manipulators
- human robot interaction
- robotic manipulator
- control policy
- trajectory tracking
- multi agent
- sagittal plane
- multiresolution
- control strategies
- robot navigation
- perceptual aliasing
- motor learning
- end effector
- control strategy
- humanoid robot
- force feedback
- autonomous learning