Abstract
Recently there has been great interest in the idea that evolvable systems based on the principles of Artificial Life can be used to continuously and autonomously adapt the behavior of physically embedded systems such as mobile robots, plants and intelligent home devices. At the same time, we have seen the introduction of evolvable hardware(EHW): new integrated circuits that are able to adapt their hardware autonomously and almost continuously to changes in the environment [11]. This paper describes how a navigation system for a physical mobile robot can be evolved using a Boolean function approach implemented on evolvable hardware. The task of the mobile robot is to track a moving target represented by a colored ball, while avoiding obstacles during its motion. Our results show that a dynamic Boolean function approach is sufficient to produce this navigation behavior. Although the classical model-free evolution method is often infeasible in the real world due to the number of possible interactions with the environment, we demonstrate that a model-based evolution method can reduce the interactions with the real world by a factor of 250, thus allowing us to apply the evolution process on-line and to obtain an adaptive tracking-avoiding system, provided the implementation can be accelerated by the utilization of evolvable hardware.
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
This is a preview of subscription content, log in via an institution.
Preview
Unable to display preview. Download preview PDF.
References
Thomas Back, Ulrich Hammel, and Hans-Paul Schwefel. Evolutionary computation: Comments on the history and current state. IEEE Transactions on Evolutionary Computation, 1(1):3–18, 1997.
Randall D. Beer and J.C. Gallagher. Evolving dynamic neural networks for adaptive behavior. Adaptive Behavior, 1(1):91–122, July 1992.
Lashon B. Booker. Classifier systems that learn internal world models. Machine Learning, 3(2–3):161–192, 1988.
Rodney Brooks. Artificial life and real robots. In F. J. Varela and P. Bourgine, editors, Proceedings of the First European Conference on Artificial Life, pages 3–10, Cambridge, MA, 1992. MIT Press / Bradford Books.
Dave Cliff, Inman Harvey, and Philip Husbands. Explorations in evolutionary robotics. Adaptive Behavior, 2(1):73–110, July 1993.
Marco Dorigo and Marco Colombetti. Robot shaping: developing autonomous agents through learning. Artificial Intelligence, 71:321–370, 1994.
Dario Floreano and Francesco Mondada. Automatic creation of an autonomous agent: Genetic evolution of a neural-network driven robot. In J-A. Meyer Dave Cliff, Philip Husbands and S. Wilson, editors, From Animals to Animats 3: Proceedings of the 3rd International Conference on Simulation of Adaptive Behavior. MIT Press, 1994.
Johan J. Grefenstette and Connie Loggia Ramsey. An approach to anytime learning. In Proceedings of the Ninth International Conference on Machine Learning, pages 189–195, San Mateo, CA., 1992. Morgan Kaufman.
John J. Grefenstette and A. Schultz.An evolutionary approach to learning in robots. In Proceedings of the Machine Learning Workshop on Robot Learning, Eleventh International Conference on Machine Learning. New Brunswick, NJ, 1994.
Inman Harvey, Philip Husbands, and Dave Cliff. Seeing the light: Artificial evolution, real vision. In J-A. Meyer Dave Cliff, Philip Husbands and S. Wilson, editors, From Animals to Animats 3: Proceedings of the 3rd International Conference on Simulation of Adaptive Behavior. MIT Press, 1994.
Tetsuya Higuchi, Tatsuya Niwa, Toshio Tanaka, Hitoshi Iba, Hugo de Garis, and T. Furuya. Evolvable hardware with genetic learning: A first step towards building a darwin machine. In Jean-Arcady Meyer, Herbert L. Roitblat, and Stewart W. Wilson, editors, Proceedings of the 2nd International Conference on the Simulation of Adaptive Behavior, pages 417–424. MIT Press, 1992.
Tsutomu Hoshino, Daisuke Mitsumoto, and Tohru Nagano. Fractal fitness landscape and loss of robustness in evolutionary robot navigation. Autonomous Robots, 5:1–16, 1988.
Philip Husbands, Inman Harvey, Dave Cliff, and Geoffrey Miller. The use of genetic algorithms for the development of sensorimotor control systems. In F. Moran, A. Moreno, J.J. Merelo, and P. Chacon, editors, Proceedings of the third European Conference on Artificial Life, pages 110–121, Granada, Spain, 1995. Springer.
Leslie Pack Kaelbling. Learning in Embedded Systems. Bradford Book, MIT Press, Cambridge, 1993.
Leslie Pack Kaelbling. Associative reinforcement learning: A generate and test algorithm. Machine Learning, 15(3):299–320, 1994.
Leslie Pack Kaelbling and Andrew W. Moore. Reinforcement learning: A survey. Journal of Artificial Intelligence Research, 4:237–277, 1996.
Didier Keymeulen, Marc Durantez, Kenji Konaka, Yasuo Kuniyoshi, and Tetsuya Higuchi. An evolutionary robot navigation system using a gate-level evolvable hardware. In Proceeding of the First International Conference on Evolvable Systems: from Biology to Hardware, pages 195–210. Springer Verlag, 1996.
Didier Keymeulen, Masaya Iwata, Kenji Konaka, Yasuo Kuniyoshi, and Tetsuya Higuchi. Evolvable hardware: a robot navigation system testbed. New Generation Computing, 16(2), 1998.
John Koza. Evolution of subsumption using genetic programming. In F. J. Varela and P. Bourgine, editors, Proceedings of the First European Conference on Artificial Life, pages 3–10, Cambridge, MA, 1992. MIT Press / Bradford Books.
Long-Ji Lin. Self-improving reactive agents based on reinforcement learning, planning and teaching. Machine Learning, 8(3–4):297–321, 1992.
Sridhar Mahadevan. Enhancing transfer in reinforcement learning by building stochastic models of robot actions. In Proceedings of the Ninth International Conference on Machine Learning, pages 290–299, 1992.
Maja Mataric and Dave Cliff. Challenges in evolving controllers for physical robots. Robotics and Autonomous Systems, 19(1):67–83, November 1996.
Masahiro Murakawa, Syuji Yoshizawa, Isamu Kajitani, and Tetsuya Higuchi. Evolvable hardware for generalized neural networks. In Martha E. Pollack, editor, Proc. of Fifteenth International Joint Conference on Artificial Intelligence, pages 1146–1151. Morgan Kaufmann Publishers, 1997.
Domenico Parisi, Stefano Nolfi, and F. Cecconi. Learning, behavior and evolution. In Proceedings of the First European Conference on Artificial Life, pages 207–216, Cambridge, MA, 1992. MIT Press / Bradford Books.
Connie Loggia Ramsey and John J. Grefenstette. Case-based initialization of genetic algorithms. In Proceedings of the fifth International Conference on Genetic Algorithms, pages 84–91, San Mateo, CA., 1993. Morgan Kaufmann.
Craig W. Reynolds. An evolved, vision-based model of obstacle avoidance behavior. In Artificial Life III, Sciences of Complexity, Proc. Vol. XVII, pages 327–346. Addison-Wesley, 1994.
Mehrdad Salami, Masaya Iwata, and Tetsuya Higuchi. Lossless image compression by evolvable hardware. In Proceedings of the Fourth European Conference on Artificial Life, Complex Adaptive Systems, pages 407–416, Boston, USA, 1997. MIT Press / Bradford Book.
Luc Steels and Rodney Brooks, editors. The Artificial Life Route to Artificial Intelligence: Building Embodied, Situated Agents. Lawrence Erlbaum Assoc, 1995.
Richard S. Sutton. Learning to predict by the method of temporal differences. Machine Learning, 3(1):9–44, 1988.
Richard S. Sutton. Integrated architectures for learning, planning, and reacting based on approximating dynamic programming. In Proceedings of the Seventh International Conference on Machine Learning, pages 216–224, 1990.
Richard S. Sutton. Planning by incremental dynamic programming. In Proceedings of the Eighth International Workshop on Machine Learning, pages 353–357. Morgan Kaufmann, 1991.
Adrian Thompson. Evolving electronic robot controllers that exploit hardware resources. In F. Moran, A. Moreno, J.J. Merelo, and P. Chacon, editors, Advances in Artificial Life: Proceedings 3rd European Conference on Artificial Life, pages 640–656, Granada, Spain, 1995. Springer-Verlag.
Christopher J.C.H. Watkins and Peter Dayan Q-learning.Machine Learning, 8(3):279–292, 1992.
Steven D. Whitehead and Dana H. Ballard. A role for anticipation in reactive systems that learn. In Proceedings of the Sixth International Conference on Machine Learning, pages 354–357, 1989.
Stewart Wilson. Classifier systems and the animat problem. Machine Learning, 2:199–228, 1987.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1998 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Keymeulen, D., Iwata, M., Konaka, K., Suzuki, R., Kuniyoshi, Y., Higuchi, T. (1998). Off-line model-free and on-line model-based evolution for tracking navigation using evolvable hardware. In: Husbands, P., Meyer, JA. (eds) Evolutionary Robotics. EvoRobots 1998. Lecture Notes in Computer Science, vol 1468. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-64957-3_74
Download citation
DOI: https://doi.org/10.1007/3-540-64957-3_74
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-64957-1
Online ISBN: 978-3-540-49902-2
eBook Packages: Springer Book Archive