Data Fusion of Robot Wrist Forces Based on Finger Force Sensors and MLF Neural Network

Abstract

Quantitative analysis of wrist forces for robot grippers is an important issue for robot control and operation safety. An approach is proposed to deduce the wrist forces from distributed force sensors in the robot fingers. A multi-layer forward (MLF) neural network is designed to fuse the data from finger force sensors. The experimental results demonstrate that the maximum deducing error of the wrist forces is decreased to 4.8% from 18.7% comparing with previous sensor fusion methods.