Jun Tani, Naohiro Fukumura
This paper discusses how a robot can learn goal-directed naviga(cid:173) tion tasks using local sensory inputs. The emphasis is that such learning tasks could be formulated as an embedding problem of dynamical systems: desired trajectories in a task space should be embedded into an adequate sensory-based internal state space so that an unique mapping from the internal state space to the motor command could be established. The paper shows that a recurrent neural network suffices in self-organizing such an adequate internal state space from the temporal sensory input. In our experiments, using a real robot with a laser range sensor, the robot navigated robustly by achieving dynamical coherence with the environment. It was also shown that such coherence becomes structurally sta(cid:173) ble as the global attractor is self-organized in the coupling of the internal and the environmental dynamics.