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.
Albiez, J. and Berns, K. (2004). Biological inspired walking—How much nature do we need?, in M. A. Armada and P. de González Santos (Eds), Climbing and Walking Robots. Proceedings of the 7th International Conference CLAWAR 2004, Springer, Berlin, pp. 357-364.
Annunziato, M. and Pizzuti, S. (2000). Adaptive parameterization of evolutionary algorithms driven by reproduction and competition, Proceedings of the European Symposium on Intelligent Techniques (ESIT 2000), Aachen, Germany, pp. 31-35.
Arabas, J. (2001). Lectures on Evolutionary Algorithms, WNT, Warsaw, (in Polish).
Bäck, T., Hoffmeister, F. and H.-P. Schwefel (1991). A survey of evolution strategies, in R. K. Belew and L. B. Booker (Eds), Proceedings of the 4th International Conference on Genetic Algorithms, Morgan Kaufmann, San Francisco, CA, pp. 2-9.
Barfoot, T. D., Earon, E. J. P. and D'Eleuterio, G. M. T. (2006). Experiments in learning distributed control for a hexapod robot, Robotics and Autonomous Systems54(10): 864-872.
Beer, R. D., Quinn, R. D., Chiel, H. J. and Ritzmann, R. E. (1997). Biologically inspired approaches to robotics: What can we learn from insects?, Communications of the ACM40(3): 31-38.
Belter, D., Kasiński, A. and Skrzypczyński, P. (2008). Evolving feasible gaits for a hexapod robot by reducing the space of possible solutions, Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, Nice, France, pp. 2673-2678.
Belter, D. and Skrzypczyński, P. (2009). Population based methods for identification and optimization of a walking robot model, in K. Kozlowski (Ed.), Robot Motion and Control 2009, Lecture Notes in Control and Information Sciences, Vol. 396, Springer, Berlin, pp. 185-195.
Busch, J., Ziegler, J., Aue, C., Ross, A., Sawitzki, D. and Banzhaf, W. (2002). Automatic generation of control programs for walking robots using genetic programming, in J. Foster, E. Lutton, J. Miller, C. Ryan and A. Tettamanzi (Eds), Genetic Programming, Proceedings of the 5th European Conference EuroGP 2002, Lecture Notes in Computer Science, Vol. 2278, Springer, Berlin, pp. 258-267.
Chernova, S. and Veloso, M. (2004). An evolutionary approach to gait learning for four-legged robots, Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, New Orleans, LA, USA, pp. 2562-2567.
Dorigo, M. and Colombetti, M. (1997). Robot Shaping: An Experiment in Behavior Engineering, MIT Press, Cambridge, MA.
Figliolini, G., Stan, S.-D. and Rea, P. (2007). Motion analysis of the leg tip of a six-legged walking robot, Proceedings of the 12th IFToMM World Congress, Besançon, France, (on CD-ROM).
Fukuoka, Y., Kimura, H. and Cohen, A. H. (2003). Adaptive dynamic walking of a quadruped robot on irregular terrain based on biological concepts, International Journal on Robotics Research22(4): 187-202.
Gallagher, J., Beer, D. R., Espenschied, K. and Quinn, R. D. (1996). Application of evolved locomotion controllers to a hexapod robot, Robotics and Autonomous Systems19(1): 95-103.
Goldberg, D. (1989). Genetic Algorithms in Search, Optimization, and Machine Learning, Addison-Wesley, Reading, MA.
Holland, J. (1975). Adaptation in Natural and Artificial Systems, University of Michigan Press, Ann Arbor, MI.
Hornby, G., Takamura, S., Yamamoto, T. and Fujita, M. (2005). Autonomous evolution of dynamic gaits with two quadruped robots, IEEE Transactions on Robotics21(3): 402-410.
Huber, M. and Grupen, R. A. (1997). A feedback control structure for on-line learning tasks, Robotics and Autonomous Systems22(3-4): 303-315.
Jakobi, N. (1998). Running across the reality gap: Octopod locomotion evolved in a minimal simulation, in P. Husbands and J.-A. Meyer (Eds), Evolutionary Robotics. Proceedings of the First European Workshop EvoRobot98, Lecture Notes in Computer Science, Vol. 1468, Springer, Berlin, pp. 39-58.
Jakobi, N., Husbands, P. and Harvey, I. (1995). Noise and the reality gap: The use of simulation in evolutionary robotics, Proceedings of the 3rd European Conference on Articial Life (ECAL'95), Granada, Spain, pp. 704-720.
Kimura, H., Yamashita, T. and Kobayashi, S. (2001). Reinforcement learning of walking behavior for a four-legged robot, Proceedings of the IEEE Conference on Decisions and Control, Orlando, FL, USA, pp. 411-416.
Kirchner, F. (1998). Q-learning of complex behaviours on a six-legged walking machine, Robotics and Autonomous Systems25(3-4): 256-263.
Kowalczuk, Z. and Białaszewski, T. (2006). Niching mechanisms in evolutionary computations, International Journal of Applied Mathematics and Computer Science16(1): 59-84.
Kozlowski, K. (1998). Modelling and Identification in Robotics, Springer, Berlin.
Kumar, V. R. and Waldron, K. J. (1989). Adaptive gait control for a walking robot, Journal of Robotic Systems6(1): 49-76.
Lewis, M., Fagg, A. and Bekey, G. (1994). Genetic algorithms for gait synthesis in a hexapod robot, in Y. Zheng (Ed.), Recent Trends in Mobile Robots, World Scientific, Singapore, pp. 317-331.
Luk, B. L., Galt, S. and Chen, S. (2001). Using genetic algorithms to establish efficient walking gaits for an eight-legged robot, International Journal of Systems Science32(6): 703-713.
Maes, P. and Brooks, R. A. (1990). Learning to coordinate behaviors, Proceedings of the 8th National Conference on Artificial Intelligence (AAAI 1990), Boston, MA, USA, pp. 796-802.
Mataric, M. and Cliff, D. (1996). Challenges in evolving controllers for physical robots, Robotics and Autonomous Systems19(1): 67-83.
Parker, G. B. and Mills, J.W. (1999). Adaptive hexapod gait control using anytime learning with fitness biasing, Proceedings of the Genetic and Evolutionary Computation Conference, Orlando, FL, USA, pp. 519-524.
Perry, M. J., Koh, C. G. and Choo, Y. S. (2006). Modified genetic algorithm strategy for structural identification, Automatica84(8-9): 529-540.
Ridderström, C. (1999). Legged locomotion control—A literature survey, Technical Report TRITA-MMK 1999:27, Royal Institute of Technology, Stockholm.
Ritzmann, R. E., Quinn, R. D. and Fischer, M. C. (2004). Convergent evolution and locomotion through complex terrain by insects, vertebrates and robots, Arthropod Structure & Development33(3): 361-379.
Skrzypczyński, P. (2004a). Experimental validation of the fuzzy reactive behaviours evolved in simulation, in F. Groen, N. Amato, A. Bonarini, E. Yoshida and B. Kröse (Eds), Intelligent Autonomous Systems 8, IOS Press, Amsterdam, pp. 464-471.
Skrzypczyński, P. (2004b). Shaping in a realistic simulation: An approach to learn reactive fuzzy rules, Preprints of the 5th IFAC/EURON Symposium on Intelligent Autonomous Vehicles, Lisbon, Portugal, (on CD-ROM).
Song, S.-M. and Waldron, K. J. (1989). Machines that Walk: The Adaptive Suspension Vehicle, MIT Press, Cambridge, MA.
Svinin, M. M., Yamada, K. and Ueda, K. (2001). Emergent synthesis of motion patterns for locomotion robots, Artificial Intelligence in Engineering15(4): 353-363.
Tuyls, K., Maes, S. and Manderick, B. (2003). Reinforcement learning in large state spaces: Simulated robotic soccer as a testbed, RoboCup 2002: Robot Soccer World Cup VI, Lecture Notes in Computer Science, Vol. 2752, Springer, Berlin, pp. 319-326.
Walas, K., Belter, D. and Kasiński, A. (2008). Control and environment sensing system for a six-legged robot, Journal of Automation, Mobile Robotics and Intelligent Systems2(3): 26-31.
Walker, J., Garrett, S. and Wilson, M. (2003). Evolving controllers for real robots: A survey of the literature, Adaptive Behavior11(3): 179-203.
Wilson, D. M. (1966). Insect walking, Annaul Reiew of Entomology11(1): 103-122.
Yang, J.-M. (2009). Fault-tolerant gait planning for a hexapod robot walking over rough terrain, Journal of Intelligent and Robotic Systems54(4): 613-627.
Zagal, J. C., Ruiz-del-Solar, J. and Vallejos, P. (2004). Back to reality: Crossing the reality gap in evolutionary robotics, Preprints of the 5th IFAC/EURON Symposium on Intelligent Autonomous Vehicles, Lisbon, Portugal, (on CD-ROM).