Applying classifier systems to learn the reactions in mobile robots

The navigation problem involves how to reach a goal avoiding obstacles in d ynamic environments. This problem can be faced considering reactions and se quences of actions. Classifier systems (CSs) have proven their ability of c ontinuous learning, however, they have some problems in reactive systems. A modified CS, namely a reactive classifier system (RCS), is proposed to ove rcome those problems. Two special mechanisms are included in the RCS: the n on-existence of internal cycles inside the CS (no internal cycles) and the fusion of environmental message with the messages posted to the message lis t in the previous instant (generation list through fusion). These mechanism s allow the learning of both reactions and sequences of actions. This learn ing process involves two main tasks: first, discriminate between rules and, second, the discovery of new rules to obtain a successful operation in dyn amic environments. Different experiments have been carried out using a mini -robot Khepera to rnd a generalized solution. The results show the ability of the system for continuous learning and adaptation to new situations.