Multisensory Learning Framework for Robot Drumming

Autor:	Barsky, A., Zito, C., Mori, H., Ogata, T., Wyatt, J. L.
Rok vydání:	2019
Předmět:	Computer Science - Robotics Computer Science - Computer Vision and Pattern Recognition Computer Science - Sound
Zdroj:	Workshop on Crossmodal Learning for Intelligent Robotics 2nd Edition. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2018
Druh dokumentu:	Working Paper
Popis:	The hype about sensorimotor learning is currently reaching high fever, thanks to the latest advancement in deep learning. In this paper, we present an open-source framework for collecting large-scale, time-synchronised synthetic data from highly disparate sensory modalities, such as audio, video, and proprioception, for learning robot manipulation tasks. We demonstrate the learning of non-linear sensorimotor mappings for a humanoid drumming robot that generates novel motion sequences from desired audio data using cross-modal correspondences. We evaluate our system through the quality of its cross-modal retrieval, for generating suitable motion sequences to match desired unseen audio or video sequences. Comment: Extended abstract
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1907.09775 Zobrazit plný text záznamu View this record from Arxiv