View-based imitation learning by conflict resolution with epipolar geometry

Imitation Learning is not simply one of the most promising ways to accelerate the behavior acquisition for humanoid robots but also one of the most interesting cognitive issues to model how we human beings learn to acquire various kinds of behaviors. However, the existing robotic approaches have focused on the behavior generation assuming the observation of the internal model of the demonstrator, but have not paid any attention how to build such a model from the learner's perception. This paper presents a computational model of view-based imitation learning without any internal model of the demonstrator. Instead, based on opt-geometric constraint (stereo epipolar constraint), the robot learns to imitate the demonstrator's motion by applying adaptive visual servoing that minimizes the residual between the recovered demonstrator's body parts supposed to be viewed by the demonstrator and the learner's ones in the learner's stereo image planes, and then reproducing the recovered demonstrator's trajectories without any reconstruction of S-D trajectories. Computer simulation and real experiment are shown and discussion is given.