论文信息 - Hierarchical neural net for learning control of a robot's arm and gripper

Hierarchical neural net for learning control of a robot's arm and gripper

A hierarchical neural network structure capable of learning the control of a robot's arm and gripper is introduced. Based on T. Kohonen's algorithm (1982) for the formation of topologically correct feature maps and on an extension of the algorithm for learning of output signals, a simulated robot arm system learns the task of grasping a cylinder. The network architecture is that of a 3-D cubic lattice in which is nested at each lattice node a 2-D square lattice. The robot learns without supervision to position its arm and to orient its gripper properly by observing its own trial movements. In a simulation, the error in positioning the manipulator after training was 0.3% of the robot's dimension, and the residual error in orienting the gripper was 3.8°. Due to cooperation between neighboring neurons during the training phase, fewer than two trial movements per neuron were sufficient to learn the required control tasks

Thomas Martinetz | Klaus Schulten

[1] Klaus Schulten,et al. Topology-conserving maps for learning visuo-motor-coordination , 1989, Neural Networks.

[2] M. Kuperstein,et al. Implementation of an adaptive neural controller for sensory-motor coordination , 1989, IEEE Control Systems Magazine.

[3] Helge Ritter,et al. Learning of Visuomotor Coordination of a Robot Arm with Redundant Degrees of Freedon , 1989 .

[4] Bernard Widrow,et al. Adaptive switching circuits , 1988 .

[5] T. M. Martinetz,et al. 3D neural net for learning visuomotor-coordination of a robot arm , 1989, International 1989 Joint Conference on Neural Networks.

[6] M. Kuperstein,et al. Implementation of an adaptive neural controller for sensory-motor coordination , 1989, International 1989 Joint Conference on Neural Networks.