Real-Time Terrain Recognition for Quadruped Robots Using Proprioceptive Sensors and Temporal Convolutional Networks

Chang, Tzu-Hsiu; Tefera, Minyechil Alehegn; Cheng, Jun-Ming; Fang, Tsung-Ming; Chen, Chin-Sheng; Lin, Chia-Jen; Peng, Peng-Chun; Ho, Chao-Ching; Tsai, Tzu-Hsuan; Su, Cherng-Yuh; Chang, Shih-Hao; Chen, Pai-Yen; Ho, Hsiang-Wei; Chang, Ching-Yuan

doi:10.3390/s26134050

This is an early access version, the complete PDF, HTML, and XML versions will be available soon.

Open AccessArticle

Real-Time Terrain Recognition for Quadruped Robots Using Proprioceptive Sensors and Temporal Convolutional Networks

by

Tzu-Hsiu Chang

¹,

Minyechil Alehegn Tefera

¹,

Jun-Ming Cheng

¹,

Tsung-Ming Fang

¹,

Chin-Sheng Chen

²,

Chia-Jen Lin

³

,

Peng-Chun Peng

⁴,

Chao-Ching Ho

¹

,

Tzu-Hsuan Tsai

⁵,

Cherng-Yuh Su

¹

,

Shih-Hao Chang

⁶,

Pai-Yen Chen

⁷,

Hsiang-Wei Ho

^8,9 and

Ching-Yuan Chang

^1,*

¹

Department of Mechanical Engineering, National Taipei University of Technology, Taipei 10608, Taiwan

²

Graduate Institute of Automation Technology, National Taipei University of Technology, Taipei 10608, Taiwan

³

Department of Electrical Engineering, National Yunlin University of Science and Technology, Douliou 64002, Taiwan

⁴

Department of Electro-Optical Engineering, National Taipei University of Technology, Taipei 10608, Taiwan

⁵

Department of Materials and Mineral Resources Engineering, National Taipei University of Technology, Taipei 10608, Taiwan

⁶

Department of Computer Science and Information Engineering, National Taipei University of Technology, Taipei 10608, Taiwan

⁷

Department of Electrical and Computer Engineering, University of Illinois Chicago, Chicago, IL 60607, USA

⁸

Department of Industrial Technology, Ministry of Economic Affairs, R.O.C., Taipei 100210, Taiwan

⁹

Department of Mechanical Engineering, Asia Eastern University of Science and Technology, New Taipei City 220303, Taiwan

^*

Author to whom correspondence should be addressed.

Sensors 2026, 26(13), 4050; https://doi.org/10.3390/s26134050 (registering DOI)

Submission received: 18 April 2026 / Revised: 19 June 2026 / Accepted: 20 June 2026 / Published: 25 June 2026

(This article belongs to the Special Issue Intelligent Robots: Control and Sensing)

Download Versions Notes

Abstract

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.

Keywords: quadruped robots; proprioceptive sensors; sensor fusion; real-time terrain classification; deep learning; temporal convolutional networks (TCNs); slip detection

Share and Cite

MDPI and ACS Style

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.; et al. Real-Time Terrain Recognition for Quadruped Robots Using Proprioceptive Sensors and Temporal Convolutional Networks. Sensors 2026, 26, 4050. https://doi.org/10.3390/s26134050

AMA Style

Chang T-H, Tefera MA, Cheng J-M, Fang T-M, Chen C-S, Lin C-J, Peng P-C, Ho C-C, Tsai T-H, Su C-Y, et al. Real-Time Terrain Recognition for Quadruped Robots Using Proprioceptive Sensors and Temporal Convolutional Networks. Sensors. 2026; 26(13):4050. https://doi.org/10.3390/s26134050

Chicago/Turabian Style

Chang, Tzu-Hsiu, Minyechil Alehegn Tefera, Jun-Ming Cheng, Tsung-Ming Fang, Chin-Sheng Chen, Chia-Jen Lin, Peng-Chun Peng, Chao-Ching Ho, Tzu-Hsuan Tsai, Cherng-Yuh Su, and et al. 2026. "Real-Time Terrain Recognition for Quadruped Robots Using Proprioceptive Sensors and Temporal Convolutional Networks" Sensors 26, no. 13: 4050. https://doi.org/10.3390/s26134050

APA Style

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

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Article metric data becomes available approximately 24 hours after publication online.

Article Menu

Real-Time Terrain Recognition for Quadruped Robots Using Proprioceptive Sensors and Temporal Convolutional Networks

Abstract

Share and Cite

Article Metrics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI