Baxendale, Mark and Nibouche, M. and Secco, Emanuele Lindo and Pipe, Tony and Pearson, M.J. (2019) Feed-forward selection of cerebellar models for calibration of robot sound source localization. In: The Living Machines Conference, 9-12 July, 2019, Nara, Japan. (Accepted for Publication)
Preview |
Text
LM2019_005_original_v3.pdf - Accepted Version Download (1MB) | Preview |
Abstract
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.
| Item Type: | Conference or Workshop Item (Paper) |
|---|---|
| Additional Information and Comments: | This is the author's version of a paper that has been accepted for presentation at the Living Machines Conference, 2019 http://livingmachinesconference.eu/2019/ |
| Faculty / Department: | Faculty of Human and Digital Sciences > Mathematics and Computer Science |
| Depositing User: | Emanuele Secco |
| Date Deposited: | 02 Jun 2019 14:26 |
| Last Modified: | 13 Jun 2019 08:49 |
| URI: | https://hira.hope.ac.uk/id/eprint/2868 |
Actions (login required)
 |
View Item |
Altmetric
Altmetric
