Multimodal Signal Processing and Learning Aspects of Human-Robot Interaction for an Assistive Bathing Robot

TL;DR

This paper presents a multimodal framework for human-robot interaction in assistive bathing robots, focusing on recognizing speech and gestures to improve elderly care, with promising recognition accuracy and privacy considerations.

Contribution

Introduces a new dataset, tools, and a multimodal recognition pipeline for assistive bathing robots, emphasizing audio and RGB-D visual streams in a real-life scenario.

Findings

Speech and gesture recognition accuracy up to 84.5% and 84% with multimodal fusion

Developed a new dataset for multimodal HRI in elderly care

Evaluated privacy aspects of RGB-D sensors in assistive robots

Abstract

We explore new aspects of assistive living on smart human-robot interaction (HRI) that involve automatic recognition and online validation of speech and gestures in a natural interface, providing social features for HRI. We introduce a whole framework and resources of a real-life scenario for elderly subjects supported by an assistive bathing robot, addressing health and hygiene care issues. We contribute a new dataset and a suite of tools used for data acquisition and a state-of-the-art pipeline for multimodal learning within the framework of the I-Support bathing robot, with emphasis on audio and RGB-D visual streams. We consider privacy issues by evaluating the depth visual stream along with the RGB, using Kinect sensors. The audio-gestural recognition task on this new dataset yields up to 84.5%, while the online validation of the I-Support system on elderly users accomplishes up to 84% when the two modalities are fused together. The results are promising enough to support further research in the area of multimodal recognition for assistive social HRI, considering the difficulties of the specific task. Upon acceptance of the paper part of the data will be publicly available.