Neural Networks Robot Controller Trained with Evolution Strategies

摘要: Neural Networks (NN) can be used as controllers in autonomous robots. The specific features of the navigation problem in robotics make the generation of good training sets for the NN very difficult. In this paper an evolution strategy (ES) is introduced to learn the weights of the NN instead of the learning method of the network. The ES is used to learn high-performance reactive behavior for navigation and collisions avoidance. No subjective information about “how to accomplish the task” has been included in the fitness function. The learned behaviors are 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. A simulator based on mini-robot Khepera has been used to learn each behavior.