AR3n: A Reinforcement Learning-based Assist-As-Needed Controller for Robotic Rehabilitation.
Shrey PareekHarris J. NisarThenkurussi KesavadasPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- augmented reality
- real time
- optimal control
- control system
- function approximation
- human computer interaction
- robotic manipulator
- control policy
- real robot
- temporal difference
- actor critic
- control loop
- mobile robot
- closed loop
- control strategy
- optimal policy
- object manipulation
- adaptive control
- markov decision processes
- virtual reality
- control scheme
- controller design
- motor learning
- robotic control
- brain injury
- initial state
- robot control
- action selection
- pid controller
- fuzzy controller
- control method
- state space
- dynamic programming
- multi agent
- neural network