AVOIDING THE WORLD MODEL TRAP - AN ACTING ROBOT DOES NOT NEED TO BE SO SMART

We propose several examples of robotics applications where interaction s with the environment play an important role, and where no modelizati on of the robot or of the world is needed, We argue that, in general, this helps to simplify the complexity of the control system, and illus trate this claim through several examples. We propose different neural networks which allow clustering of scattered objects by several robot s, learning of obstacle avoidance and learning of target retrieval.