Style-transfer based Speech and Audio-visual Scene Understanding for Robot Action Sequence Acquisition from Videos
Abstract
To realize human-robot collaboration, robots need to execute actions for new tasks according to human instructions given finite prior knowledge. Human experts can share their knowledge of how to perform a task with a robot through multi-modal instructions in their demonstrations, showing a sequence of short-horizon steps to achieve a long-horizon goal. This paper introduces a method for robot action sequence generation from instruction videos using (1) an audio-visual Transformer that converts audio-visual features and instruction speech to a sequence of robot actions called dynamic movement primitives (DMPs) and (2) style-transfer-based training that employs multi-task learning with video captioning and weakly-supervised learning with a semantic classifier to exploit unpaired video-action data. We built a system that accomplishes various cooking actions, where an arm robot executes a DMP sequence acquired from a cooking video using the audio-visual Transformer. Experiments with Epic-Kitchen-100, YouCookII, QuerYD, and in-house instruction video datasets show that the proposed method improves the quality of DMP sequences by 2.3 times the METEOR score obtained with a baseline video-to-action Transformer. The model achieved 32% of the task success rate with the task knowledge of the object.
Keywords
Cite
@article{arxiv.2306.15644,
title = {Style-transfer based Speech and Audio-visual Scene Understanding for Robot Action Sequence Acquisition from Videos},
author = {Chiori Hori and Puyuan Peng and David Harwath and Xinyu Liu and Kei Ota and Siddarth Jain and Radu Corcodel and Devesh Jha and Diego Romeres and Jonathan Le Roux},
journal= {arXiv preprint arXiv:2306.15644},
year = {2023}
}
Comments
Accepted to Interspeech2023