Real-Robot Deep Reinforcement Learning: Improving Trajectory Tracking of Flexible-Joint Manipulator with Reference Correction.
Dmytro PavlichenkoSven BehnkePublished in: ICRA (2022)
Keyphrases
- real robot
- trajectory tracking
- control law
- reinforcement learning
- closed loop
- mobile robot
- visual servoing
- control system
- dynamic model
- bi directional
- control algorithm
- sliding mode
- iterative learning
- nonlinear systems
- physical constraints
- control theory
- control scheme
- control strategy
- iterative learning control
- simulated robot
- adaptive control
- motion planning
- optimal control
- robotic systems
- control method
- multi robot
- autonomous robots
- variable structure
- dynamical systems
- real world
- humanoid robot
- stability analysis
- model free
- degrees of freedom
- robot control
- adaptive fuzzy
- experimental data
- learning process
- control parameters