2024-03-29T23:36:23Zhttps://ipsj.ixsq.nii.ac.jp/ej/?action=repository_oaipmhoai:ipsj.ixsq.nii.ac.jp:002229442023-11-14T00:51:14Z06164:06165:09654:11122
A prototype of multi-modal interaction robot based on emotion estimation method using physiological signalsA prototype of multi-modal interaction robot based on emotion estimation method using physiological signalsenghttp://id.nii.ac.jp/1001/00222835/Conference Paperhttps://ipsj.ixsq.nii.ac.jp/ej/?action=repository_action_common_download&item_id=222944&item_no=1&attribute_id=1&file_no=1Copyright (c) 2022 by the Information Processing Society of JapanShibaura Institute of TechnologyShibaura Institute of TechnologyShibaura Institute of TechnologyShibaura Institute of TechnologyKaoru, SuzukiTakumi, IguchiYuri, NakagawaMidori, SugayaIn recent years, the type of robot that estimates emotions in real time has been proposed and is expected to be introduced into nursing care and home use. Among emotion estimation technologies, those incorporating methods using the physiological signals have satisfied the requirements of obtaining real-time emotional response of the human by using physiological signals such as EEG and HRV from the wearable sensors. However, the current real-time emotion estimation response robot only has a speech function or a facial expression function accordingly to emotional states of the human that is in front of the robot and does not use multiple modalities. With those limited modalities of output, we assume that it would be difficult to improve the emotional state of the person that uses the robot. And we would like to know which modalities are effective and what happens when modalities are combined. Therefore, in this research, we propose a multi-modal robot that combines not only speech but also facial expressions and body movements aiming the practical application of a robot that responds to the person's emotion in real time. This robot outputs facial expressions/speeches/body movements to improve or maintain the user's emotional state. As a result of the experiment, it is confirmed that this robot has a relaxing effect on the user when output includes speech.In recent years, the type of robot that estimates emotions in real time has been proposed and is expected to be introduced into nursing care and home use. Among emotion estimation technologies, those incorporating methods using the physiological signals have satisfied the requirements of obtaining real-time emotional response of the human by using physiological signals such as EEG and HRV from the wearable sensors. However, the current real-time emotion estimation response robot only has a speech function or a facial expression function accordingly to emotional states of the human that is in front of the robot and does not use multiple modalities. With those limited modalities of output, we assume that it would be difficult to improve the emotional state of the person that uses the robot. And we would like to know which modalities are effective and what happens when modalities are combined. Therefore, in this research, we propose a multi-modal robot that combines not only speech but also facial expressions and body movements aiming the practical application of a robot that responds to the person's emotion in real time. This robot outputs facial expressions/speeches/body movements to improve or maintain the user's emotional state. As a result of the experiment, it is confirmed that this robot has a relaxing effect on the user when output includes speech.Proceedings of Asia Pacific Conference on Robot IoT System Development and Platform20227122022-12-202022-12-14