Feed-Forward Selection of Cerebellar Models for Calibration of Robot Sound Source Localization

• Published in: Biomimetic and Biohybrid Systems Vol. 11556; pp. 3 - 14
• Main Authors: Baxendale, M. D., Nibouche, M., Secco, E. L., Pipe, A. G., Pearson, M. J.
• Format: Book Chapter
• Language: English
• Published: Switzerland Springer International Publishing AG 2019; Springer International Publishing
• Series: Lecture Notes in Computer Science
• Subjects: Adaptive filter; Cerebellum; Multiple models; Responsibility prediction; Robot audition
• DOI: 10.1007/978-3-030-24741-6_1
• ISBN: 9783030247409; 3030247406
• ISSN: 0302-9743

We present a responsibility predictor, based on the adaptive filter model of the cerebellum, to provide feed-forward selection of cerebellar calibration models for robot Sound Source Localization (SSL), based on audio features extracted from the received audio stream. In previous work we described a system that selects the models based on sensory feedback, however, a drawback of that system is that it is only able to select a set of calibrators a-posteriori, after action (e.g. orienting a camera toward the sound source after a position estimate is made). The responsibility predictor improved the system performance compared to that without responsibility prediction. We show that a trained responsibility predictor is able to use contextual signals in the absence of ground truth to successfully select models with a performance approaching that of a system with full access to the ground truth through sensory feedback.