Frustration as a way toward autonomy and self-improvement in robotic navigation.
Résumé
Autonomy and self-improvment capabilities are still challenging in the fields of robotics. Allowing a robot to autonomously navigate wide and unknown environments not only requires a set of robust strategies to cope with miscellaneous situations, but also needs mechanisms of self-assesment for guiding learning and monitoring strategies. Monitoring strategies requires feedbacks on the behavior's quality, from a given fitness system, to take correct decisions. In this work, we focuse on how an emotional controller can be used to modulate robot behaviors. Following an incremental and constructivist approach, we present a generic neural architecture, based on an online novelty detection algorithm, that may be able to self-evaluate any sensori-motor strategies. This architecture learns contingencies between sensations and actions, giving the expected sensation based from the previous perception. Prediction error, coming from surprising events, provides a direct measure of the quality of the underlying sensori-motor contingencies involved. We show how a simple emotional controller based on the prediction progress allows the system to monitor its strategies to solve complex navigation tasks and communicate its disability in deadlock situations. We propose that this model could be a key structure toward self-monitoring. We made several experiments that can account for such properties for different behaviors (road following and Place Cells based navigation).