Abstract
Evolutionary algorithms have been successfully used to create controllers for many animats. However, intuitive fitness functions like the survival time of the animat, often do not lead to interesting results because of the bootstrap problem, arguably one of the main challenges in evolutionary robotics: if all the individuals perform equally poorly, the evolutionary process cannot start. To overcome this problem, many authors defined ordered sub-tasks to bootstrap the process, leading to an incremental evolution scheme. Published methods require a deep knowledge of the underlying structure of the analyzed task, which is often not available to the experimenter. In this paper, we propose a new incremental scheme based on multi-objective evolution. This process is able to automatically switch between each sub-task resolution and does not require to order them. The proposed method has been successfully tested on the evolution of a neuro-controller for a complex-light seeking simulated robot, involving 8 sub-tasks.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Meyer, J.A.: From natural to artificial life: Biomimetic mechanisms in animat design. Robotics and Autonomous Systems 22(3-21) (1997)
Meyer, J.A., Husbands, P., Harvey, I.: Evolutionary robotics: a survey of applications and problems. In: Husbands, P., Meyer, J.A. (eds.) Proceedings of The First European Workshop on Evolutionary Robotics - EvoRobot 1998. Springer, Heidelberg (1998)
Kodjabachian, J., Meyer, J.A.: Evolution and development of neural networks controlling locomotion, gradient-following, and obstacle-avoidance in artificial insects. IEEE Transactions on Neural Networks 9, 796–812 (1997)
Urzelai, J., Floreano, D., Dorigo, M., Colombetti, M.: Incremental robot shaping. Connection Science Journal 10(384), 341–360 (1998)
Harvey, I., Husbands, P., Cliff, D.: Seeing the light: artificial evolution; real vision. In: Cliff, D., Husbands, P., Meyer, J.A., Wilson, S. (eds.) From Animals to Animats 3, Proceedings of the third international conference on Simulation of Adaptive Behavior. MIT Press/Bradford Books (1994)
Gomez, F., Miikkulainen, R.: Incremental evolution of complex general behavior. Adaptive Behavior 5, 317–342 (1997)
Urzelai, J., Floreano, D.: Incremental Evolution with Minimal Resources. In: Proceedings of IKW 1999 (1999)
Deb, K.: Multi-objectives optimization using evolutionnary algorithms. Wiley, Chichester (2001)
Winkeler, J., Manjunath, B.: Incremental evolution in genetic programming. Genetic Programming, 403–411 (1998)
Walker, M.: Comparing the performance of incremental evolution to direct evolution. In: 2nd International Conference on Autonomous Robots and Agents (2004)
Parker, G.: The Incremental Evolution of Gaits for Hexapod Robots. In: Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2001), pp. 1114–1121 (2001)
Mouret, J.B., Doncieux, S., Meyer, J.A.: Incremental evolution of target-following neuro-controllers for flapping-wing animats. In: From Animals to Animats: Proceedings of the 9th International Conference on the Simulation of Adaptive Behavior (SAB), pp. 606–618 (2006)
Larsen, T., Hansen, S.: Evolving composite robot behaviour-a modular architecture. In: Proceedings of the Fifth International Workshop. Robot Motion and Control 2005, pp. 271–276 (2005)
De Nardi, R., Togelius, J., Holland, O., Lucas, S.: Evolution of Neural Networks for Helicopter Control: Why Modularity Matters. In: IEEE Congress on Evolutionary Computation, 2006. CEC 2006, pp. 1799–1806 (2006)
Nolfi, S., Paris, D.: Evolving non-Trivial Behaviors on Real Robots: an Autonomous Robot that Picks up Objects. In: Topics in Artificial Intelligence: Proceedings of 4th Conference of the Italian Association for Artificial Intelligence, AI* IA 1995, Florence, Italy, October 11-13 (1995)
Deb, K., Mohan, M., Mishra, S.: Evaluating the ε-domination based multi-objective evolutionary algorithm for a quick computation of pareto-optimal solutions. Evolutionary Computatition 13(4), 501–525 (2005)
Doncieux, S., Meyer, J.A.: Evolving PID-like neurocontrollers for non-linear control problems. International Journal of Control and Intelligent Systems (IJCIS) 33(1), 55–62 (2005); Special Issue on nonlinear adaptive PID control
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Mouret, JB., Doncieux, S. (2008). Incremental Evolution of Animats’ Behaviors as a Multi-objective Optimization. In: Asada, M., Hallam, J.C.T., Meyer, JA., Tani, J. (eds) From Animals to Animats 10. SAB 2008. Lecture Notes in Computer Science(), vol 5040. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-69134-1_21
Download citation
DOI: https://doi.org/10.1007/978-3-540-69134-1_21
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-69133-4
Online ISBN: 978-3-540-69134-1
eBook Packages: Computer ScienceComputer Science (R0)