Variable Impedance Control in End-Effector Space: An Action Space for Reinforcement Learning in Contact-Rich Tasks.
Roberto Martín-MartínMichelle A. LeeRachel GardnerSilvio SavareseJeannette BohgAnimesh GargPublished in: IROS (2019)
Keyphrases
- action space
- impedance control
- reinforcement learning
- end effector
- manipulation tasks
- model free
- state space
- markov decision processes
- optimal control
- real valued
- degrees of freedom
- force feedback
- action selection
- force control
- vision system
- robot arm
- inverse kinematics
- position control
- transfer learning
- optimal policy
- markov decision process
- stochastic processes
- robot manipulators
- function approximation
- robotic manipulator
- robot navigation
- visual servoing
- real robot
- motion planning
- dynamic programming
- single agent
- robotic arm
- multi agent
- learning algorithm
- real time
- human robot interaction
- robotic systems