Abstract
Evolutionary robotics has been shown to be an effective technique for generating robot behaviors that are difficult to derive analytically from the robot’s mechanics and task environment. Moreover, augmenting evolutionary algorithms with environmental scaffolding via an incremental shaping method makes it possible to evolve controllers for complex tasks that would otherwise be infeasible. In this paper we present a summary of two recent publications in the evolutionary robotics literature demonstrating how these methods can be used to evolve robot controllers for non-trivial tasks, what the obstacles are in evolving controllers in this way, and present a novel research question that can be investigated under this framework.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Anderson, M.: Embodied Cognition: A field guide. Artificial Intelligence 149(1), 91–130 (2003)
Auerbach, J., Bongard, J.C.: Evolution of functional specialization in a morphologically homogeneous robot. In: Proceedings of the Genetic and Evolutionary Computation Conference, GECCO (2009)
Auerbach, J., Bongard, J.C.: How robot morphology and training order affect the learning of multiple behaviors. In: Proceedings of the IEEE Congress on Evolutionary Computation, CEC (2009)
Beer, R.: The Dynamics of Active Categorical Perception in an Evolved Model Agent. Adaptive Behavior 11(4), 209 (2003)
Beer, R.D.: Parameter space structure of continuous-time recurrent neural networks. Neural Comp. 18(12), 3009–3051 (2006)
Beer, R.D.: The dynamics of brain-body-environment systems: A status report. In: Calvo, P., Gomila, A. (eds.) Handbook of Cognitive Science: An Embodied Approach, pp. 99–120. Elsevier, Amsterdam (2008)
Bongard, J.: Behavior chaining: incremental behavioral integration for evolutionary robotics. In: Bullock, S., Noble, J., Watson, R., Bedau, M.A. (eds.) Artificial Life XI: Proceedings of the Eleventh International Conference on the Simulation and Synthesis of Living Systems, pp. 64–71. MIT Press, Cambridge (2008)
Brooks, R.: A robust layered control system for a mobile robot. IEEE Journal of Robotics and Automation, [legacy, pre - 1988] 2(1), 14–23 (1986), http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1087032
Brooks, R.: Cambrian intelligence. MIT Press, Cambridge (1999)
Calabretta, R., Nolfi, S., Parisi, D., Wagner, G.P.: Duplication of modules facilitates the evolution of functional specialization. Artificial Life 6(1), 69–84 (2000)
Dorigo, M., Colombetti, M.: Robot shaping: Developing situated agents through learning. Artificial Intelligence 70(2), 321–370 (1994)
Harvey, I., Husbands, P., Cliff, D., Thompson, A., Jakobi, N.: Evolutionary robotics: the sussex approach. Robotics and Autonomous Systems 20, 205–224 (1997)
Hornby, G., Takamura, S., Yamamoto, T., Fujita, M.: Autonomous evolution of dynamic gaits with two quadruped robots. IEEE Transactions on Robotics 21(3), 402–410 (2005), doi:10.1109/TRO.2004.839222
Izquierdo, E., Buhrmann, T.: Analysis of a dynamical recurrent neural network evolved for two qualitatively different tasks: walking and chemotaxis. In: Bullock, S., Noble, J., Watson, R., Bedau, M.A. (eds.) Artificial Life XI: Proceedings of the Eleventh International Conference on the Simulation and Synthesis of Living Systems, pp. 257–264. MIT Press, Cambridge (2008)
Noë, A.: Action in Perception. MIT Press, Cambridge (2004)
Nolfi, S., Floreano, D.: Evolutionary Robotics: The Biology,Intelligence,and Technology. MIT Press, Cambridge (2000)
Pfeifer, R., Bongard, J.: How the Body Shapes the Way We Think: A New View of Intelligence. MIT Press, Cambridge (2006)
Reil, T., Husbands, P.: Evolution of central pattern generators for bipedal walking in a real-time physics environment. IEEE Transactions on Evolutionary Computation 6(2), 159–168 (2002), doi:10.1109/4235.996015
Saksida, L., Raymond, S., Touretzky, D.S.: Shaping robot behavior using principles from instrumental conditioning. Robotics and Autonomous Systems 22, 231–249 (1997)
Singh, S.P.: Transfer of learning across sequential tasks. Machine Learning 8, 323–339 (1992)
Wood, D., Bruner, J., Ross, G.: The role of tutoring in problem solving. J. Child Psychol. Psychiatry 17(2), 89–100 (1976)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Auerbach, J.E., Bongard, J.C. (2011). Evolving Monolithic Robot Controllers through Incremental Shaping. In: Doncieux, S., Bredèche, N., Mouret, JB. (eds) New Horizons in Evolutionary Robotics. Studies in Computational Intelligence, vol 341. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-18272-3_5
Download citation
DOI: https://doi.org/10.1007/978-3-642-18272-3_5
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-18271-6
Online ISBN: 978-3-642-18272-3
eBook Packages: EngineeringEngineering (R0)