Model-Free Design Optimization of a Hopping Robot and Its Comparison With a Human Designer.
Kaur Aare SaarFabio GiardinaFumiya IidaPublished in: IEEE Robotics Autom. Lett. (2018)
Keyphrases
- model free
- reinforcement learning
- human robot interaction
- mobile robot
- visual servoing
- human robot
- reinforcement learning algorithms
- temporal difference
- human users
- function approximation
- policy iteration
- human operators
- learning algorithm
- robot manipulators
- robot navigation
- robotic systems
- path planning
- neural network
- control scheme
- closed loop
- support vector machine
- manipulation tasks