参考文献:1. Crespi, A, Lachat, D, Pasquier, A, Ijspeert, AJ (2008) Controlling swimming and crawling in a fish robot using a central pattern generator. Auton. Robots 25: pp. 3-13 CrossRef 2. Lee, WP, Hallam, J, Lund, HH Learning complex robot behaviours by evolutionary computing with task decomposition. In: Birk, A, Demiris, J eds. (1998) Learning Robots. Springer, Heidelberg, pp. 155-172 CrossRef 3. Whiteson, S, Kohl, N, Miikkulainen, R, Stone, P (2005) Evolving soccer keepaway players through task decomposition. Mach. Learn. 59: pp. 5-30 CrossRef 4. Lessin, D., Fussell, D., Miikkulainen, R.: Open-ended behavioral complexity for evolved virtual creatures. In: Proceedings of the GECCO 2013, p. 335. ACM Press, New York, USA (2013) 5. Rossi, C, Eiben, AE (2014) Simultaneous versus incremental learning of multiple skills by modular robots. Evol. Intell. 7: pp. 119-131 CrossRef 6. Stone, P, Veloso, MM Layered learning. In: Mantaras, RL, Plaza, E eds. (2000) Machine Learning: ECML 2000. Springer, Heidelberg, pp. 369-381 CrossRef 7. Gomez, F, Miikkulainen, R (1997) Incremental evolution of complex general behavior. Adapt. Behav. 5: pp. 317-342 CrossRef 8. Bongard, J (2008) Behavior chaining: incremental behavioral integration for evolutionary robotics. Artif. Life XI Number 1976: pp. 64-71 9. Auerbach, J., Bongard, J.C.: How robot morphology and training order affect the learning of multiple behaviors. In: IEEE Congress on CEC 2009, pp. 39鈥?6, Trondheim, May 2009 10. Bongard, J.C.: Morphological and environmental scaffolding synergize when evolving robot controllers. In: GECCO 2011 1st workshop on evolutionary computation for designing generic algorithms, p. 179. ACM Press, Dublin, Ireland (2011) 11. Mukosaka, N, Tanev, I, Shimohara, K (2013) Performance of incremental genetic programming on adaptability of snake-like Robot. IES2013 24: pp. 152-157 12. Kuyucu, T., Tanev, I., Shimohara, K.: Genetic transposition inspired incremental genetic programming for efficient coevolution of locomotion and sensing of simulated snake-like robot. In: Proceedings of the Eleventh European Conference on the Synthesis and Simulation of Living Systems ECAL-2011, pp. 439鈥?46. MIT Press, Paris (2011) 13. Song, G.B., Cho, S.B.: Combining incrementally evolved neural networks based on cellular automata for complex adaptive behaviors. In: First IEEE Symposium on Combinations of Evolutionary Computation and Neural Networks, pp. 121鈥?29. IEEE, San Antonio, TX (2000) 14. Mouret, J-B, Doncieux, S Incremental Evolution of animats鈥?behaviors as a multi-objective optimization. In: Asada, M, Hallam, JCT, Meyer, J-A, Tani, J eds. (2008) From Animals to Animats 10. Springer, Heidelberg, pp. 210-219 CrossRef 15. Rohmer, E., Singh, S.P.N., Freese, M.: V-REP: A versatile and scalable robot simulation framework. In: 26th IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2013), pp. 1321鈥?326. IEEE, Tokyo, November 2013 16. Jantapremjit, P., Austin, D.: Design of a modular self-reconfigurable robot. In: Australian Conference on Robotics and Automation. Citeseer, Sydney, Australia (2001) 17. Moreno, R., Gomez, J.: Simple chain type modular robot hardware (2011). https://www.youtube.com/watch?v=x6UQfC4KALA 18. Storn, R, Price, K (1997) Differential evolutiona simple and efficient heuristic for global optimization over continuous spaces. J. Global Optim. 11: pp. 341-359 CrossRef 19. Caamano, P., Tedin, R., Paz-Lopez, A., Becerra, J.A.: JEAF: A Java Evolutionary Algorithm Framework. In: IEEE Congress on Evolutionary Computation, CEC 2010, pp. 1鈥?, December 2007. IEEE, Barcelona, July 2010 20. Jakobi, N (1997) Evolutionary robotics and the radical envelope-of-noise hypothesis. Adapt. Behav. 6: pp. 325-368 CrossRef
作者单位:Applications of Evolutionary Computation
丛书名:978-3-319-16548-6
刊物类别:Computer Science
刊物主题:Artificial Intelligence and Robotics Computer Communication Networks Software Engineering Data Encryption Database Management Computation by Abstract Devices Algorithm Analysis and Problem Complexity
出版者:Springer Berlin / Heidelberg
ISSN:1611-3349
文摘
In this paper we aim to develop a controller that allows a robot to traverse an structured environment. The approach we use is to decompose the environment into simple sub-environments that we use as basis for evolving the controller. Specifically, we decompose a narrow corridor environment into four different sub-environments and evolve controllers that generalize to traverse two larger environments composed of the sub-environments. We also study two strategies for presenting the sub-environments to the evolutionary algorithm: all sub-environments at the same time and in sequence. Results show that by using a sequence the evolutionary algorithm can find a controller that performs well in all sub-environments more consistently than when presenting all sub-environments together. We conclude that environment decomposition is an useful approach for evolving controllers for structured environments and that the order in which the decomposed sub-environments are presented in sequence impacts the performance of the evolutionary algorithm.