Neural network learning control of robot manipulators using gradually increasing task difficulty
- Jet Propulsion lab., Pasadena, CA (United States)
Trajectory Extension Learning is an incremental method for training an artificial neural network to approximate the inverse dynamics of a robot manipulator. Training data near a desired trajectory is obtained by slowly varying a parameter of the trajectory from a region of easy solvability of the inverse dynamics toward the desired behavior. The parameter can be average speed, path shape, feedback gain, or any other controllable variable. As learning proceeds, an approximate solution to the local inverse dynamics for each value of the parameter is used to guide learning for the next value of the parameter. Convergence conditions are given for two variations on the algorithm. Examples are shown of application to a real 2-joint direct drive robot arm and a simulated 3-joint redundant arm, both using simulated equilibrium point control.
- OSTI ID:
- 7255614
- Journal Information:
- IEEE Transactions on Robotics and Automation (Institute of Electrical and Electronics Engineers); (United States), Vol. 10:3; ISSN 1042-296X
- Country of Publication:
- United States
- Language:
- English
Similar Records
Optimal point-to-point motion control of robots with redundant degrees of freedom
Minimum-time trajectory control of a two-link flexible robotic manipulator