English

Multisensory Learning Framework for Robot Drumming

Robotics 2019-07-24 v1 Computer Vision and Pattern Recognition Sound

Abstract

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.

Keywords

Cite

@article{arxiv.1907.09775,
  title  = {Multisensory Learning Framework for Robot Drumming},
  author = {A. Barsky and C. Zito and H. Mori and T. Ogata and J. L. Wyatt},
  journal= {arXiv preprint arXiv:1907.09775},
  year   = {2019}
}

Comments

Extended abstract

R2 v1 2026-06-23T10:28:06.536Z