In this paper, a new coevolutive method, called Uniform Coevolution, is introduced to learn weights of a neural network controller in autonomous robots. An evolutionary strategy is used to learn high-performance reactive behavior for navigation and collisions avoidance. The introduction of coevolutive over evolutionary strategies allows evolving the environment, to learn a general behavior able to solve the problem in different environments. Using a traditional evolutionary strategy method, without coevolution, the learning process obtains a specialized behavior. All the behaviors obtained, with/without coevolution have been tested in a set of environments and the capability of generalization is shown for each learned behavior. A simulator based on a mini-robot Khepera has been used to learn each behavior. The results show that Uniform Coevolution obtains better generalized solutions to examples-based problems. ; Publicado
Neural network controller against environment: A coevolutive approach to generalize robot navigation behavior
2002-02-01
33
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
DDC: | 629 |
A general learning co-evolution method to generalize autonomous robot navigation behavior
BASE | 2000
|British Library Online Contents | 2003
|TECHNOLOGY TO GENERALIZE SAFE DRIVING EXPERIENCES FOR AUTOMATED VEHICLE BEHAVIOR PREDICTION
Europäisches Patentamt | 2021
|TECHNOLOGY TO GENERALIZE SAFE DRIVING EXPERIENCES FOR AUTOMATED VEHICLE BEHAVIOR PREDICTION
Europäisches Patentamt | 2021
|Technology to generalize safe driving experiences for automated vehicle behavior prediction
Europäisches Patentamt | 2023
|