MomentumNet-CD: Real-Time Collision Detection for Industrial Robots Based on Momentum Observer with Optimized BP Neural Network
Open Access
Abstract
The accurate detection and identification of collision states in industrial robot environments is a critically important and challenging task. Deep learning-based methods have been widely applied to collision detection; however, these methods primarily rely on dynamic models and dynamic threshold settings, which are subject to modeling errors and threshold adjustment latency. To address this issue, we propose MomentumNet-CD, a novel collision detection method for industrial robots that leverages backpropagation (BP) neural networks. MomentumNet-CD extracts collision state features through a momentum observer and constructs an observation model using Mahalanobis distance. These features are then processed by an optimized three-layer BP neural network for accurate collision identification. The network is trained using a modified Levenberg–Marquardt algorithm by introducing regularization terms and continuous probability outputs. Furthermore, we developed a comprehensive acquisition system based on the Q8-USB data acquisition card and the QUARC 2.7 real-time control environment. The system integrates key hardware components including a MR-J2S-70A servo driver, ATI six-dimensional force/torque (F/T) sensor, and ISO-U2-P1-F8 isolation transmitter, and the corresponding software module is developed through MATLAB/Simulink R2022b, which achieves the high-frequency real-time acquisition of critical robot joint states. The experimental results show that the MomentumNet-CD method achieves an overall accuracy of 93.65% under five different speed conditions, and the detection delay is only 12.16 ms. Compared with the existing methods, the method shows obvious advantages in terms of the accuracy and response speed of collision detection.Keywords
Funding Information
- Talent Program of the State Administration for Market Regulation (QNBJ202319, FJMS2023016)
- Research Project of Fujian Provincial Market Supervision Bureau (QNBJ202319, FJMS2023016)
This publication has 32 references indexed in Scilit:
- Research on Zero-Force control and collision detection of deep learning methods in collaborative robotsDisplays, 2025
- Collision detection and fault diagnosis with DMAO-GRU for flow regulating valveMeasurement Science and Technology, 2024
- A bio-inspired visual collision detection network integrated with dynamic temporal variance feedback regulated by scalable functional countering jitter streamingNeural Networks, 2024
- A compound planning algorithm considering both collision detection and obstacle avoidance for intelligent demolition robotsRobotics and Autonomous Systems, 2024
- A novel collision detection method based on current residuals for robots without joint torque sensors: A case study on UR10 robotRobotics and Computer-Integrated Manufacturing, 2024
- Dynamic collision estimator for collaborative robots: A dynamic Bayesian network with Markov model for highly reliable collision detectionRobotics and Computer-Integrated Manufacturing, 2023
- Human-robot Collision Detection Based on the Improved Camshift Algorithm and Bounding BoxInternational Journal of Control, Automation, and Systems, 2022
- Human–robot collisions detection for safe human–robot interaction using one multi-input–output neural networkSoft Computing, 2019
- New tactile sensor for position detection based on distributed planar electric fieldSensors and Actuators A: Physical, 2016
- The Mahalanobis distanceChemometrics and Intelligent Laboratory Systems, 2000