Model-free and model-based time-optimal control of a badminton robot.
M. LiuBruno DepraetereGregory PinteIvo GrondmanRobert BabuskaPublished in: ASCC (2013)
Keyphrases
- model free
- optimal control
- reinforcement learning
- control problems
- risk sensitive
- function approximation
- reinforcement learning algorithms
- real robot
- mobile robot
- dynamic programming
- feedback control
- policy iteration
- infinite horizon
- human robot interaction
- robotic systems
- temporal difference
- impedance control
- control law
- markov decision processes
- state space
- learning algorithm
- autonomous robots
- optimal control problems
- humanoid robot
- control strategy
- robot manipulators
- robot navigation
- linear quadratic
- continuous stirred tank reactor
- service robots
- average cost
- policy gradient
- manipulation tasks
- force control
- motion planning
- machine learning
- neural network