论文信息 - Using PSOMs to Learn Inverse Kinematics Through Virtual Decomposition of the Robot

Using PSOMs to Learn Inverse Kinematics Through Virtual Decomposition of the Robot

We propose a technique to speed up the learning of the inverse kinematics of a robot manipulator by decomposing it into two or more virtual robot arms. Unlike previous decomposition approaches, this one does not place any requirement on the robot architecture and, thus, it is completely general. Parametrized Self-Organizing Maps (PSOM) are particularly adequate for this type of learning, and permit comparing results obtained directly and through the decomposition. Experimentation shows that time reductions of up to two orders of magnitude are easily attained.

Carme Torras | Vicente Ruiz de Angulo | C. Torras | V. R. D. Angulo

[1] Carme Torras. Robot control , 1998 .

[2] Carme Torras,et al. Speeding up the learning of robot kinematics through function decomposition , 2005, IEEE Transactions on Neural Networks.

[3] Jirí Benes,et al. On neural networks , 1990, Kybernetika.

[4] Kevin N. Gurney,et al. An introduction to neural networks , 2018 .

[5] Helge J. Ritter,et al. Neural computation and self-organizing maps - an introduction , 1992, Computation and neural systems series.

[6] Helge J. Ritter,et al. Three-dimensional neural net for learning visuomotor coordination of a robot arm , 1990, IEEE Trans. Neural Networks.

[7] C. Gielen,et al. Neural computation and self-organizing maps, an introduction , 1993 .

[8] David C. Sterratt,et al. Does Morphology Influence Temporal Plasticity? , 2002, ICANN.

[9] C. S. G. Lee,et al. Robotics: Control, Sensing, Vision, and Intelligence , 1987 .

[10] Carme Torras,et al. Learning Inverse Kinematics via Cross-Point Function Decomposition , 2002, ICANN.

[11] Carme Torras,et al. Self-calibration of a space robot , 1997, IEEE Trans. Neural Networks.

[12] Helge J. Ritter,et al. Rapid learning with parametrized self-organizing maps , 1996, Neurocomputing.

[13] Klaus Schulten,et al. Implementation of self-organizing neural networks for visuo-motor control of an industrial robot , 1993, IEEE Trans. Neural Networks.