Low-latency classification of social haptic gestures using transformers
- Author
- Qiaoqiao Ren (UGent) , Yuanbo Hou (UGent) and Tony Belpaeme (UGent)
- Organization
- Abstract
- Social touch, and its recognition and classification, is increasingly important in human-robot interaction. We present a Transformer-based model trained and evaluated on an open-source dataset. The dataset, the Human-Animal Affective Robot Touch (HAART) dataset, was collected for the 2015 Recognition of Touch Gesture Challenge (RTGC 2015) and contains different haptic actions directed at a robotic animal. The actions are recorded using a multi-resolution pressure sensor. We feed the output, containing the touch type to the Nao robot to make the robot sense the touch type. The proposed transformer-based gesture classification model achieved 72.8% classification accuracy in 2.67 seconds, which outperforms the best-submitted algorithm of the RTGC 2015 which has a test classification accuracy of 70.9 % and needed 8 seconds.
- Keywords
- Attention mechanism, Transformer, Convolutional neural networks, Gestures classification, Social touch interaction
Downloads
-
(...).pdf
- full text (Published version)
- |
- UGent only
- |
- |
- 960.37 KB
Citation
Please use this url to cite or link to this publication: http://hdl.handle.net/1854/LU-01GVZ72PCY5Y7Q9QQT2667QY9T
- MLA
- Ren, Qiaoqiao, et al. “Low-Latency Classification of Social Haptic Gestures Using Transformers.” COMPANION OF THE ACM/IEEE INTERNATIONAL CONFERENCE ON HUMAN-ROBOT INTERACTION, HRI 2023, Association for Computing Machinery (ACM), 2023, pp. 137–41, doi:10.1145/3568294.3580059.
- APA
- Ren, Q., Hou, Y., & Belpaeme, T. (2023). Low-latency classification of social haptic gestures using transformers. COMPANION OF THE ACM/IEEE INTERNATIONAL CONFERENCE ON HUMAN-ROBOT INTERACTION, HRI 2023, 137–141. https://doi.org/10.1145/3568294.3580059
- Chicago author-date
- Ren, Qiaoqiao, Yuanbo Hou, and Tony Belpaeme. 2023. “Low-Latency Classification of Social Haptic Gestures Using Transformers.” In COMPANION OF THE ACM/IEEE INTERNATIONAL CONFERENCE ON HUMAN-ROBOT INTERACTION, HRI 2023, 137–41. New York: Association for Computing Machinery (ACM). https://doi.org/10.1145/3568294.3580059.
- Chicago author-date (all authors)
- Ren, Qiaoqiao, Yuanbo Hou, and Tony Belpaeme. 2023. “Low-Latency Classification of Social Haptic Gestures Using Transformers.” In COMPANION OF THE ACM/IEEE INTERNATIONAL CONFERENCE ON HUMAN-ROBOT INTERACTION, HRI 2023, 137–141. New York: Association for Computing Machinery (ACM). doi:10.1145/3568294.3580059.
- Vancouver
- 1.Ren Q, Hou Y, Belpaeme T. Low-latency classification of social haptic gestures using transformers. In: COMPANION OF THE ACM/IEEE INTERNATIONAL CONFERENCE ON HUMAN-ROBOT INTERACTION, HRI 2023. New York: Association for Computing Machinery (ACM); 2023. p. 137–41.
- IEEE
- [1]Q. Ren, Y. Hou, and T. Belpaeme, “Low-latency classification of social haptic gestures using transformers,” in COMPANION OF THE ACM/IEEE INTERNATIONAL CONFERENCE ON HUMAN-ROBOT INTERACTION, HRI 2023, Stockholm, Sweden, 2023, pp. 137–141.
@inproceedings{01GVZ72PCY5Y7Q9QQT2667QY9T,
abstract = {{Social touch, and its recognition and classification, is increasingly important in human-robot interaction. We present a Transformer-based model trained and evaluated on an open-source dataset. The dataset, the Human-Animal Affective Robot Touch (HAART) dataset, was collected for the 2015 Recognition of Touch Gesture Challenge (RTGC 2015) and contains different haptic actions directed at a robotic animal. The actions are recorded using a multi-resolution pressure sensor. We feed the output, containing the touch type to the Nao robot to make the robot sense the touch type. The proposed transformer-based gesture classification model achieved 72.8% classification accuracy in 2.67 seconds, which outperforms the best-submitted algorithm of the RTGC 2015 which has a test classification accuracy of 70.9 % and needed 8 seconds.}},
author = {{Ren, Qiaoqiao and Hou, Yuanbo and Belpaeme, Tony}},
booktitle = {{COMPANION OF THE ACM/IEEE INTERNATIONAL CONFERENCE ON HUMAN-ROBOT INTERACTION, HRI 2023}},
isbn = {{9781450399708}},
keywords = {{Attention mechanism,Transformer,Convolutional neural networks,Gestures classification,Social touch interaction}},
language = {{eng}},
location = {{Stockholm, Sweden}},
pages = {{137--141}},
publisher = {{Association for Computing Machinery (ACM)}},
title = {{Low-latency classification of social haptic gestures using transformers}},
url = {{http://doi.org/10.1145/3568294.3580059}},
year = {{2023}},
}
- Altmetric
- View in Altmetric
- Web of Science
- Times cited: