Real-Time Terrain Recognition for Quadruped Robots Using Proprioceptive Sensors and Temporal Convolutional Networks
Sensors · 25.06.2026 · 26 (13) · 4050
DOI: 10.3390/s26134050 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 25.06.2026. Verfasst von Tzu-Hsiu Chang und 13 weiteren Autor:innen. Beteiligte Einrichtung: Department of Mechanical Engineering, National Taipei University of Technology, Taipei 10608, Taiwan. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science and Technology Council.
Abstract (Originalsprache)
In this article, we propose a novel real-time terrain recognition and slip estimation method for quadruped robots using proprioceptive sensors and temporal convolutional networks (TCNs). As quadruped robots are increasingly deployed in complex environments, accurate terrain understanding is crucial. External sensors can be affected by lighting variations, occlusion, reflective surfaces, and others. To overcome these challenges, we propose a proprioceptive sensing-based complementary perception module with a TCN, enabling reliable real-time terrain recognition while reducing dependence on external perception. The TCN model effectively captures temporal dependencies in sensor signals, enabling precise and robust detection. The framework is validated through extensive real-world experiments and deployed on an embedded edge computing platform for real-time operation. Results show that the proposed TCN method achieves 98.8% recognition accuracy, outperforming the baseline models compared in this study. In addition, this study analyzes how locomotion speed and environmental conditions affect slip in quadruped robots. These findings confirm that quadruped robots can not only recognize terrain types but also detect surface states, enabling safer and more adaptive locomotion. Therefore, the proposed system is a cost-effective, robust, and low-latency solution for real-time terrain recognition, providing a strong foundation for future deployment across more diverse terrains.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Mechanical Engineering, National Taipei University of Technology, Taipei 10608, Taiwan.
- Graduate Institute of Automation Technology, National Taipei University of Technology, Taipei 10608, Taiwan.
- Department of Electrical Engineering, National Yunlin University of Science and Technology, Douliou 64002, Taiwan.
- Department of Electro-Optical Engineering, National Taipei University of Technology, Taipei 10608, Taiwan.
- Department of Materials and Mineral Resources Engineering, National Taipei University of Technology, Taipei 10608, Taiwan.
- Department of Computer Science and Information Engineering, National Taipei University of Technology, Taipei 10608, Taiwan.
ORCID-Profile: Chia-Jen Lin, Chao-Ching Ho, Cherng-Yuh Su
Förderung
- National Science and Technology Council
Zitieren
APA
Chang, T. H., Tefera, M. A., Cheng, J. M., Fang, T. M., Chen, C. S., Lin, C. J., Peng, P. C., Ho, C. C., Tsai, T. H., Su, C. Y., Chang, S. H., Chen, P. Y., Ho, H. W., & Chang, C. Y. (2026). Real-Time Terrain Recognition for Quadruped Robots Using Proprioceptive Sensors and Temporal Convolutional Networks. Sensors, 26(13), 4050. https://doi.org/10.3390/s26134050
Vancouver
Chang TH, Tefera MA, Cheng JM, Fang TM, Chen CS, Lin CJ, et al. Real-Time Terrain Recognition for Quadruped Robots Using Proprioceptive Sensors and Temporal Convolutional Networks. Sensors. 2026;26(13):4050. doi:10.3390/s26134050
BibTeX
@article{Chang2026,
author = {Chang, Tzu-Hsiu and Tefera, Minyechil Alehegn and Cheng, Jun-Ming and Fang, Tsung-Ming and Chen, Chin-Sheng and Lin, Chia-Jen and Peng, Peng-Chun and Ho, Chao-Ching and Tsai, Tzu-Hsuan and Su, Cherng-Yuh and Chang, Shih-Hao and Chen, Pai-Yen and Ho, Hsiang-Wei and Chang, Ching-Yuan},
title = {Real-Time Terrain Recognition for Quadruped Robots Using Proprioceptive Sensors and Temporal Convolutional Networks},
journal = {Sensors},
year = {2026},
volume = {26},
number = {13},
pages = {4050},
doi = {10.3390/s26134050}
}
EUVIMED