M. Gouko, N. Tomi, T. Nagano, and K. Ito
Emergent behaviour, self-organized learning, multiple tasks, mobilerobot
We propose a self-organized learning model that can generate be- haviours for successfully performing various tasks, unlike conven- tional systems that can perform only a limited task in a limited environment. The model memorizes various relationships between changes in sensory information and a motor command through learning. After the learning, the model can perform various tasks by generating the various behaviours automatically. We investigated the performance of the model by applying it to a mobile robot simulation. In the simulation, we applied two different tasks to the model, which performed the same learning. The results indicate that suitable behaviours for all the tasks emerged spontaneously. We also investigated the effectiveness of online learning for the model.
Important Links:
Go Back
