Berlanga de Jesús, AntonioMolina López, José ManuelSanchis de Miguel, María AraceliIsasi, Pedro2009-04-172009-04-171999Engineering applications of bio-inspired artificial neural networks. Berlin: Springer, 1999. p. 516-525 (Lecture Notes in Computer Science; 1607)978-3-540-66068-21611-3349 (Online)https://hdl.handle.net/10016/4006Proceeding of: International Work-Conference on Artificial and Natural Neural Networks, IWANN'99 Alicante, Spain, June 2–4, 1999In this paper an evolution strategy (ES) is introduced, to learn weights of a neural network controller in autonomous robots. An ES is used to learn high-performance reactive behavior for navigation and collisions avoidance. The learned behavior is able to solve the problem in different environments; so, the learning process has proven the ability to obtain a specialized behavior. All the behaviors obtained have been tested in a set of environment and the capability of generalization is showed for each learned behavior. No subjective information about “how to accomplish the task” has been included in the fitness function. A simulator based on mini-robot Khepera has been used to learn each behavior.application/pdfeng© Springerconference paperInformática10.1007/BFb0100519open access516525Engineering applications of bio-inspired artificial neural networks