A biologically inspired approach to feasible gait learning for a hexapod robot

A biologically inspired approach to feasible gait learning for a hexapod robot The objective of this paper is to develop feasible gait patterns that could be used to control a real hexapod walking robot. These gaits should enable the fastest movement that is possible with the given robot's mechanics and drives on a flat terrain. Biological inspirations are commonly used in the design of walking robots and their control algorithms. However, legged robots differ significantly from their biological counterparts. Hence we believe that gait patterns should be learned using the robot or its simulation model rather than copied from insect behaviour. However, as we have found tahula rasa learning ineffective in this case due to the large and complicated search space, we adopt a different strategy: in a series of simulations we show how a progressive reduction of the permissible search space for the leg movements leads to the evolution of effective gait patterns. This strategy enables the evolutionary algorithm to discover proper leg co-ordination rules for a hexapod robot, using only simple dependencies between the states of the legs and a simple fitness function. The dependencies used are inspired by typical insect behaviour, although we show that all the introduced rules emerge also naturally in the evolved gait patterns. Finally, the gaits evolved in simulations are shown to be effective in experiments on a real walking robot.

[1]  Giorgio Figliolini,et al.  Motion analysis of the leg tip of a six-legged walking robot , 2007 .

[2]  Chan Ghee Koh,et al.  Modified genetic algorithm strategy for structural identification , 2006 .

[3]  Gary B. Parker,et al.  Adaptive hexapod gait control using anytime learning with fitness biasing , 1999 .

[4]  Frank Kirchner,et al.  Q-learning of complex behaviours on a six-legged walking machine , 1997, Proceedings Second EUROMICRO Workshop on Advanced Mobile Robots.

[5]  K. Tuyls,et al.  Reinforcement Learning in Large State Spaces , 2002, RoboCup.

[6]  Mauro Annunziato,et al.  Adaptive Parameterization of Evolutionary Algorithms and Chaotic Populations , 2002, Advances in Computational Intelligence and Learning.

[7]  Richard Horn,et al.  Electronic performance support systems , 1997, CACM.

[8]  Tim D. Barfoot,et al.  Experiments in learning distributed control for a hexapod robot , 2006, Robotics Auton. Syst..

[9]  Masahiro Fujita,et al.  Autonomous evolution of dynamic gaits with two quadruped robots , 2005, IEEE Transactions on Robotics.

[10]  Jung-Min Yang,et al.  Fault Tolerant Gait Planning for a Hexapod Robot with MultipleLocked Joint Failures , 2003, MLMTA.

[11]  Jan Albiez,et al.  Biological Inspired Walking — How Much Nature Do We Need? , 2005 .

[12]  Yasuhiro Fukuoka,et al.  Adaptive Dynamic Walking of a Quadruped Robot on Irregular Terrain Based on Biological Concepts , 2003, Int. J. Robotics Res..

[13]  Rodney A. Brooks,et al.  Learning to Coordinate Behaviors , 1990, AAAI.

[14]  Manuela M. Veloso,et al.  An evolutionary approach to gait learning for four-legged robots , 2004, 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE Cat. No.04CH37566).

[15]  Dave Cliff,et al.  Challenges in evolving controllers for physical robots , 1996, Robotics Auton. Syst..

[16]  George A. Bekey,et al.  Genetic Algorithms for Gait Synthesis in a Hexapod Robot , 1994 .

[17]  Frank Kirchner.  Q-learning of complex behaviours on a six-legged walking machine , 1998, Robotics Auton. Syst..

[18]  Inman Harvey,et al.  Noise and the Reality Gap: The Use of Simulation in Evolutionary Robotics , 1995, ECAL.

[19]  Jung-Min Yang.  Fault-Tolerant Gait Planning for a Hexapod Robot Walking over Rough Terrain , 2009, J. Intell. Robotic Syst..

[20]  Piotr Skrzypczyński.  Shaping in a realistic simulation: An approach to learn reactive fuzzy rules , 2004 .

[21]  Karl Tuyls,et al.  Reinforcement learning in large state spaces: Simulated robotic soccer as a testbed , 2003 .

[22]  S. Pizzuti,et al.  Adaptive Parameterization of Evolutionary Algorithms Driven by Reproduction and Competition , 2000 .

[23]  Zdzisław Kowalczuk,et al.  Niching mechanisms in evolutionary computations , 2006 .

[24]  Kenneth J. Waldron,et al.  Machines That Walk: The Adaptive Suspension Vehicle , 1988 .

[25]  Marco Colombetti,et al.  Robot Shaping: An Experiment in Behavior Engineering , 1997 .

[26]  Vijay R. Kumar,et al.  Adaptive gait control for a walking robot , 1989, J. Field Robotics.

[27]  Nick Jacobi,et al.  Running Across the Reality Gap: Octopod Locomotion Evolved in a Minimal Simulation , 1998, EvoRobot.

[28]  Thomas Bäck,et al.  A Survey of Evolution Strategies , 1991, ICGA.

[29]  Dominik Belter,et al.  Population-based Methods for Identification and Optimization of a Walking Robot Model , 2009 .

[30]  Randall D. Beer,et al.  Biologically inspired approaches to robotics: what can we learn from insects? , 1997, CACM.

[31]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[32]  Krzysztof Kozłowski,et al.  Modelling and Identification in Robotics , 1998 .

[33]  Krzysztof Walas,et al.  Control and environment sensing system for a six-legged robot , 2008 .

[34]  R. Quinn,et al.  Convergent evolution and locomotion through complex terrain by insects, vertebrates and robots. , 2004, Arthropod structure & development.

[35]  Shigenobu Kobayashi,et al.  Reinforcement learning of walking behavior for a four-legged robot , 2001, Proceedings of the 40th IEEE Conference on Decision and Control (Cat. No.01CH37228).

[36]  Piotr Skrzypczynski,et al.  Evolving feasible gaits for a hexapod robot by reducing the space of possible solutions , 2008, 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[37]  Javier Ruiz-del-Solar,et al.  Back to reality: Crossing the reality gap in evolutionary robotics , 2004 .

[38]  山田 祐,et al.  Open Dynamics Engine を用いたスノーボードロボットシミュレータの開発 , 2007 .

[39]  Wolfgang Banzhaf,et al.  Automatic Generation of Control Programs for Walking Robots Using Genetic Programming , 2002, EuroGP.

[40]  D. Wilson.  Insect walking. , 1966, Annual review of entomology.

[41]  Sheng Chen,et al.  Using genetic algorithms to establish efficient walking gaits for an eight-legged robot , 2001, Int. J. Syst. Sci..

[42]  Randall D. Beer,et al.  Application of evolved locomotion controllers to a hexapod robot , 1996, Robotics Auton. Syst..

[43]  Kazuaki Yamada,et al.  Emergent synthesis of motion patterns for locomotion robots , 2001, Artif. Intell. Eng..

[44]  D. E. Goldberg,et al.  Genetic Algorithms in Search , 1989 .

[45]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[46]  Roderic A. Grupen,et al.  A feedback control structure for on-line learning tasks , 1997, Robotics Auton. Syst..

[47]  Joanne H. Walker,et al.  Evolving Controllers for Real Robots: A Survey of the Literature , 2003, Adapt. Behav..