A method to learn the inverse kinematics of multi-link robots by evolving neuro-controllers

A general method to learn the inverse kinematic of multi-link robots by means of neuro-controllers is presented. We can find analytical solutions for the most used and well-known robots in the literature. However, these solutions are specific to a particular robot configuration and are not generally applicable to other robot morphologies. The proposed method is general in the sense that it is independent of the robot morphology. The method is based on the evolutionary computation paradigm and works obtaining incrementally better neuro-controllers. Furthermore, the proposed method solves some specific issues in robotic neuro-controller learning: it avoids any neural network learning algorithm which relies on the classical supervised input-target learning scheme and hence it lets to obtain neuro-controllers without providing targets. It can converge beyond local optimal solutions, which is one of the main drawbacks of some neural network training algorithms based on gradient descent when applied to highly redundant robot morphologies. Furthermore, using learning algorithms such as the neuro-evolution of augmenting topologies it is also possible to learn the neural network topology which is a common source of empirical testing in neuro-controllers design. Finally, experimental results are provided when applying the method to two multi-link robot learning tasks and a comparison between structural and parametric evolutionary strategies on neuro-controllers is shown.

[1]  Javier de Lope,et al.  A Biomimetic Approach for the Stability of Biped Robots , 2005 .

[2]  Risto Miikkulainen,et al.  Evolving Neural Networks through Augmenting Topologies , 2002, Evolutionary Computation.

[3]  Nikolaus Hansen,et al.  Adapting arbitrary normal mutation distributions in evolution strategies: the covariance matrix adaptation , 1996, Proceedings of IEEE International Conference on Evolutionary Computation.

[4]  Peter J. Angeline,et al.  An evolutionary algorithm that constructs recurrent neural networks , 1994, IEEE Trans. Neural Networks.

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

[6]  Stefan Roth,et al.  Covariance Matrix Adaptation for Multi-objective Optimization , 2007, Evolutionary Computation.

[7]  Alan S. Morris,et al.  Finding the inverse kinematics of manipulator arm using artificial neural network with lookup table , 1997, Robotica.

[8]  Y. Kurematsu,et al.  Autonomous trajectory generation of a biped locomotive robot using neuro oscillator , 1993, IEEE International Conference on Neural Networks.

[9]  Javier de Lope Asiaín,et al.  Solving the Inverse Kinematics in Humanoid Robots: A Neural Approach , 2009, IWANN.

[10]  Michael I. Jordan,et al.  Forward Models: Supervised Learning with a Distal Teacher , 1992, Cogn. Sci..

[11]  J. Denavit,et al.  A kinematic notation for lower pair mechanisms based on matrices , 1955 .

[12]  Javier de Lope Asiaín,et al.  Inverse Kinematics for Humanoid Robots Using Artificial Neural Networks , 2003, EUROCAST.

[13]  Pablo J. Alsina,et al.  Robot inverse kinematics: a modular neural network approach , 1995, 38th Midwest Symposium on Circuits and Systems. Proceedings.