A study of Morphological Computation by using Probabilistic Inference for Motor Planning

One key idea behind morphological computation is that many difficulties of a control problem can be absorbed by the morphology of a robot. The performance of the controlled system naturally depends on the control architecture and on the morphology of the robot. Because of this strong coupling most of the impressive applications in morphological computation typically apply minimalistic control architectures. Ideally, adapting the morphology of the plant and optimizing the control law interact such that finally, optimal physical properties of the system and optimal control laws emerge. As a first step towards this vision we apply optimal control methods for investigating the power of morphological computation. We use a probabilistic optimal control method to acquire control laws given the current morphology. We show that by changing the morphology of our robot, control problems can be simplified, resulting in optimal controllers with reduced complexity and higher performance. This concept is evaluated on a compliant 4-link model of a humanoid robot, which has to keep balance in the presence of external pushes.

[1]  E. Todorov,et al.  A generalized iterative LQG method for locally-optimal feedback control of constrained nonlinear stochastic systems , 2005, Proceedings of the 2005, American Control Conference, 2005..

[2]  Christopher G. Atkeson,et al.  Multiple balance strategies from one optimization criterion , 2007, 2007 7th IEEE-RAS International Conference on Humanoid Robots.

[3]  L. Munari.  How the body shapes the way we think — a new view of intelligence , 2009 .

[4]  Marc Toussaint,et al.  Robot trajectory optimization using approximate inference , 2009, ICML '09.

[5]  Vicenç Gómez,et al.  Optimal control as a graphical model inference problem , 2009, Machine Learning.

[6]  Bernhard Schölkopf,et al.  Learning Inverse Dynamics: a Comparison , 2008, ESANN.

[7]  R. Pfeifer,et al.  Self-Organization, Embodiment, and Biologically Inspired Robotics , 2007, Science.

[8]  Robert J. Wood,et al.  Design, fabrication, and analysis of a 3DOF, 3cm flapping-wing MAV , 2007, 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[9]  H. Kappen.  An introduction to stochastic control theory, path integrals and reinforcement learning , 2007 .

[10]  Helmut Hauser,et al.  Towards a theoretical foundation for morphological computation with compliant bodies , 2011, Biological Cybernetics.

[11]  Fumiya Iida,et al.  Sensing through body dynamics , 2006, Robotics Auton. Syst..

[12]  Jan Peters,et al.  Relative Entropy Inverse Reinforcement Learning , 2011, AISTATS.

[13]  Marc Toussaint,et al.  An Approximate Inference Approach to Temporal Optimization in Optimal Control , 2010, NIPS.

[14]  Stefan Schaal,et al.  Incremental Online Learning in High Dimensions , 2005, Neural Computation.

[15]  Pieter Abbeel,et al.  Apprenticeship learning via inverse reinforcement learning , 2004, ICML.

[16]  Petros Koumoutsakos,et al.  Reducing the Time Complexity of the Derandomized Evolution Strategy with Covariance Matrix Adaptation (CMA-ES) , 2003, Evolutionary Computation.

[17]  Duy Nguyen-Tuong,et al.  Local Gaussian Process Regression for Real Time Online Model Learning , 2008, NIPS.

[18]  H. Sebastian Seung,et al.  Learning to Walk in 20 Minutes , 2005 .