Reinforcement Learning Enabled Automatic Impedance Control of a Robotic Knee Prosthesis to Mimic the Intact Knee Motion in a Co-Adapting Environment.
Ruofan WuMinhan LiZhikai YaoJennie SiHe HuangPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- mobile robot
- impedance control
- robot motion
- manipulation tasks
- real robot
- real time
- robotic systems
- model free
- motion planning
- joint angles
- robot control
- autonomous robots
- optimal control
- function approximation
- human motion
- image sequences
- dynamic environments
- position control
- motion capture
- camera motion
- human operators
- feature points
- state space
- optical flow
- moving objects