Control Engineering Practice · 2026

Sensorless contact forces estimation for robotic manipulators using dual-stage temporal-residual neural network compensation

Y. Zhou, Y. H. Cheung, S. Liu, F. C. Law, Y. Shi, L. Han, M. Duan

Online article · November 2026 issue

Overview

A hybrid model estimates end-effector contact forces and moments from robot signals. Two stages of temporal-residual learning compensate dynamics errors and remaining wrench errors, with uncertainty estimates and experimental comparisons.

Citation

Zhou, Y., Cheung, Y. H., Liu, S., Law, F. C., Shi, Y., Han, L., and Duan, M. (2026). Sensorless contact forces estimation for robotic manipulators using dual-stage temporal-residual neural network compensation. Control Engineering Practice, 176, 107140.