ST-HMR: A Robust Collision Detection Framework for Collaborative Robots Based on Dual-Domain Interaction and Manifold Regularization
- 12 June 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ASME Transactions on Mechatronics
- Vol. PP (10834435) , 1-9
Abstract
As physical human–robot interaction (pHRI) becomes increasingly prevalent in unstructured industrial environments, ensuring contact safety under complex dynamics remains a critical challenge. External sensors can detect contact effectively, but their cost and integration complexity limit industrial scalability. Sensorless approaches are more economical, yet many data-driven methods ignore frequency-domain mechanical noise, rely on single-scale temporal modeling, and remain vulnerable to unknown anomalies. To address these issues, this article proposes ST-HMR, a sensorless collision-detection framework that relies exclusively on intrinsic proprioceptive signals, including joint angles, joint velocities, and measured joint motor currents. The framework is organized around three interrelated components: ST-GIM derives frequency-aware gates from each proprioceptive window to suppress drivetrain noise, dilated temporal pyramid aggregation aggregates short- and long-range temporal responses for both abrupt impacts and compliant contacts, and hypersphere manifold regularization constructs a compact normal-operation manifold for robust anomaly scoring. Experiments on a UR5e robot show that ST-HMR achieves 94.75% accuracy and an AUC of 0.9814 while maintaining specificity above 96%, providing a practical sensorless solution for industrial robot safety.Keywords
Funding Information
- National Natural Science Foundation of China
- Basic Research Program for PhD Students (524B2049)
- National Natural Science Foundation of China Young Scientist Fund Program (52522502)
This publication has 20 references indexed in Scilit:
- High-precision fuzzy-based force measurement and control with a novel air-suspended frictionless polishing pneumatic end-actuatorPrecision Engineering, 2026
- FcaNet: Frequency Channel Attention Networks2021
- MVTec AD — A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection2019
- Collision Detection for Industrial Collaborative Robots: A Deep Learning ApproachIEEE Robotics and Automation Letters, 2019
- Survey on human–robot collaboration in industrial settings: Safety, intuitive interfaces and applicationsMechatronics, 2018
- LSTM Fully Convolutional Networks for Time Series ClassificationIEEE Access, 2017
- Temporal Convolutional Networks for Action Segmentation and Detection2017
- Collision detection, isolation and identification for humanoids2017
- Safe Physical Human-Robot Interaction: Measurements, Analysis and New Insights2010
- An atlas of physical human–robot interactionMechanism and Machine Theory, 2008