Abstract
Evolutionary computation is a powerful learning method that has successfully been used to evolve control programs for autonomous robots. Nevertheless, its practical use has been limited by a significant problem. Most evolutionary computation methods operate on a population of possible solutions, which all must be tested to attain their fitness. Testing the entire population of solutions on the actual robot is impractical for all but the simplest problems. Conducting the tests on a simulation of the robot significantly saves time and wear on the robot, but requires an accurate model of the robot, which is in itself is a difficult task, and does not accommodate for changes in the performance of the robot, which are commonplace once it is in operation. In this chapter, we present a method for linking the simulation to the actual robot to allow the learning system to learn even when the simulation is not completely accurate and adapt the control program for changes in the robot’s capabilities. The method’s viability is demonstrated by its application to learning the control program for an actual hexapod robot’s performing area coverage.
This is a preview of subscription content, log in via an institution to check access.
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
Jakobi, N.: Half-baked, ad-hoc and noisy: minimal simulations for evolutionary robotics. In: Advances in artificial life: Proceedings of the 4th european conference on artificial life (1997)
Schultz, A., Grefenstette, J., Adams, W.: RoboShepherd: learning a complex behavior. In: Proceedings of the robots and learning workshop (RoboLearn) (1996)
Lee, W.-P., Hallam, J., Lund, H.: Applying genetic programming to evolve behavior primitives and arbitrators for mobile robots. In: Proceedings of IEEE 4th international conference on evolutionary computation (1997)
Harvey, I.: Artificial evolution and real robots. In: Proceedings of international symposium on artificial life and robotics (AROB), pp. 138–141 (1996)
Mondada, F., Floreano, D.: Evolution of neural control structures: some experiments on mobile robots. Robotics and autonomous systems 16 (1995)
Mahdavi, S., Bentley: An evolutionary approach to damage recovery of robot motion with muscles. In: Seventh European conference on artificial life (2003)
Lund, H., Miglino, O.: From simulated to real robots. In: Proceedings of IEEE 3rd international conference on evolutionary computation (1996)
Miglino, O., Lund, H., Nolfi, S.: Evolving mobile robots in simulated and real environments. Technical report, Institute of Psychology, CNR, Rome (1995)
Floreano, D., Urzelai, J.: Evolution of plastic control networks. Autonomous robots 11(3), 311–317 (2001)
Watson, R., Ficici, S., Pollack, J.: Embodied evolution: distributing an evolutionary algorithm in a population of robots. Robotics and autonomous systems 39(1), 1–18 (2002)
Husbands, P., Harvey, I., Cliff, D., Miller, G.: Artificial evolution: a new path for artificial intelligence? Brain and cognition 34, 130–159 (1997)
Mataric, M., Cliff, D.: Challenges in evolving controllers for physical robots. Evolutional robotics, special issue of robotics and autonomous systems 19(1), 67–83 (1996)
Nolfi, S., Florano, D., Miglino, O., Mondada, F.: How to evolve autonomous robots: different approaches in evolutionary robotics. In: Proceedings of the international workshop on the synthesis and simulation of living systems (1994)
Zelinsky, A., Jarvis, R., Byrne, J., Yuta, S.: Planning paths of complete coverage of an unstructured environment by a mobile robot. In: Proceedings of international conference on advanced robotics, pp. 533–538 (1993)
Choset, H., Pignon, P.: Coverage path planning: the boustrophedon cellular decomposition. In: Proceedings of the international conference on field and service robotics (1997)
Acar, E., Zhang, Y., Choset, H., Schervish, M., Costa, A., Melamud, R., Lean, D., Graveline, A.: Path planning for robotic demining and development of a test platform. In: Proceedings of the 3rd international conference on field and service robots (FSR), pp. 161–168 (2001)
Acar, E., Choset, H., Rizzi, A., Atkar, P., Hull, D.: Morse decompositions for coverage tasks. The international journal of robotics research 21(4) (2002)
Ollis, M., Stentz, A.: Vision-based perception for an autonomous harvester. In: Proceedings of the IEEE/RSJ international conference on intelligent robotic systems (1997)
Hofner, C., Schmidt, G.: Path planning and guidance techniques for autonomous mobile cleaning robot. Robotics and autonomous systems 14 (1995)
Icking, C., Kamphans, T., Klein, R., Langetepe, E.: Exploring simple grid polygons. In: Proceedings of the 11th international computing and combinatorics conference (2005)
Jager, M., Nebel, B.: Dynamic decentralization area partitioning for cooperating cleaning robots. In: IEEE international conference on robotics and automation (ICRA 2002) (2002)
Parker, G.: Evolving gaits for hexapod robots using cyclic genetic algorithms. International journal of general systems 34(3) (June 2005)
Parker, G., Rawlins, G.: Cyclic genetic algorithms for the locomotion of hexapod robots. In: Proceedings of the world automation congress (WAC 1996), Robotic and Manufacturing Systems, vol. 3, pp. 617–622 (1996)
Holland, J.: Adaptation in natural and artificial systems. The University of Michigan Press, Ann Arbor (1975)
Parker, G.: Evolving Cyclic control for a hexapod robot performing area coverage. In: Proceedings of 2001 IEEE international symposium on computational intelligence in robotics and automation (CIRA 2001), pp. 561–566 (2001)
Dean, T., Boddy, M.: An analysis of time-dependent planning. In: Proceedings of the seventh national conference on AI (AAAI 1988) (1988)
Grefenstette, J., Ramsey, C.: An approach to anytime learning. In: Proceedings of the ninth international conference on machine learning (1992)
Lund, H., Cuenca, V., Hallam J.: A simple real-time mobile robot tracking system. Technical paper 41, Dept of AI, University of Edinburgh (1996)
Parker, G., Mills, J.: Adaptive hexapod gait control using anytime learning with fitness biasing. In: Proceedings of the genetic and evolutionary computation conference (GECCO 1999), pp. 519–524 (1999)
Parker, G.: Fitness biasing to produce adaptive gaits for hexapod robots. In: Proceedings of the 2004 IEEE/RSJ international conference on intelligent robots and systems (IROS 2004), pp. 2843–2848 (2004)
Parker, G.: Co-Evolving model parameters for anytime learning in evolutionary robotics. Robotics and autonomous systems 33(1) (October 31, 2000)
Goldberg, D., Deb, K., Korb, B.: Don’t worry, be messy. In: Proceedings of the fourth international conference in genetic algorithms and their applications (1991)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Parker, G.B. (2009). Punctuated Anytime Learning to Evolve Robot Control for Area Coverage. In: Liu, D., Wang, L., Tan, K.C. (eds) Design and Control of Intelligent Robotic Systems. Studies in Computational Intelligence, vol 177. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-89933-4_13
Download citation
DOI: https://doi.org/10.1007/978-3-540-89933-4_13
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-89932-7
Online ISBN: 978-3-540-89933-4
eBook Packages: EngineeringEngineering (R0)