This paper presents an autonomous evolutionary system applied to control a mobile robot in unknown environments. The navigation system learns efficiently to deal with situations where the robot must capture targets avoiding collisions with obstacles. Toward this end, robot direction and speed must be properly defined. The evolutionary approach is based on a version of classifier systems, responsible for the proposition of a competitive process involving rules of elementary behaviour. A virtual environment is used to evolve the controller, a Khepera II robot is submitted to real navigation tasks, with no significant degradation in performance. As an additional experiment, the controller is also evolved in a real environment, and validated in a different and more complex environment, not previously experimented, attesting the generalization capability of the proposal. © 2003 IEEE.1574580Arkin, R.C., (1998) Behavior-based Robotics, , The MIT PressCazangi, R.R., Figueiredo, M.F., Simultaneous emergence of conflicting basic behaviors and their coordination in an evolutionary autonomous navigation system (2002) Proceedings of the 2002 Congress on Evolutionary Computation (CEC'2002), pp. 466-471. , Honolulu, EUACrestani Jr., P.R., Von Zuben, F.J., Figueiredo, M.F., A hierarchical neuro-fuzzy approach to autonomous navigation (2002) Proceedings of the IEEE International Joint Conference on Neural Networks (IJCNN'2002), pp. 2339-2344. , Honolulu, EUAFigueiredo, M., Gomide, F., Evolving neurofuzzy networks for basic behaviors and a recategorization approach for their'coordination (1996) Genetic Algorithms and Soft Computing, pp. 533-552. , Herrera, F. and Verdegay, J. eds, Physica-VerlagFloreano, D., Mondada, F., Hardware solutions for evolutionary robotics (1998) Proceedings of the I European Workshop of Evolutionary Robotics, pp. 137-151. , P. Husbands and J-A. Meyer, Springer-VerlagFogel;, D.B., (1999) Evolutionary Computation - Toward a New Philosophy of Machine Intelligence, , 2nd edition, IEEE PressGrefenstette, J.J., A system for learning control strategies with genetic algorithms (1989) Proceedings of the III ICGA, Morgan Kaufmann, pp. 183-190Holland, J.H., Escaping brittleness: The possibilities of general-purpose learning algorithms applied to parallel rule-based systems (1986) Machine Learning: An Artificial Intelligence Approach, pp. 593-623. , Michalsky, R. S., Carbonell, J. G. and Mitchell, T. M., eds., Morgan Kaufmannhttp://www.kteam.com/robots/kheperaLanzi, P.L., Stolzmann, W., Wilson, S.W., Learning classifier systems. from foundations to applications (2000) Lecture Notes in Artificial Intelligence, 1813. , Springer-VerlagMondada, F., Franzi, E., Jenne, P., Mobile robot miniaturisation: A tool for investigating in control algorithms (1993) Proceedings of the III International Symposium on Experimental Robotics, pp. 501-513. , T. Yoshikawa and F. Miyazaki, eds., Springer-Verlag, BerlinMondada, F., Verschure, P.F.M.J., Modeling system-environment interaction: The complementary roles of simulations and real world artifacts (1993) Proceedings of the II European Conference on Artificial Life (ECAL'93), pp. 808-817. , BrusselsPfeifer, R., Scheier, C., (1999) Understanding Intelligence, , MLT PressRichards, R.A., (1995) Zero, H-order Shape Optimization Utilizing Learning Classifier Systems, , PhD Thesis, Stanford UniversitySteels, L., When are robots intelligent autonomous agents? (1995) Journal of Robotics and Autonomous Systems, 15, pp. 3-9Verschure, P.F.M.J., A bottom up approach towards the acquisition and expression of sequential representations applied to a behaving real-world device: Distributed adaptive control III (1998) Neural Networks, 11, pp. 1531-1549Wilson, M., King, C., Hunt, J., Evolving hierarchical robot behaviors (1997) Robotics and Autonomous Systems, 22 (3-4), pp. 215-230