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

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.

[1]  Bin Liang,et al.  Multisensory gripper and local autonomy of extravehicular mobile robot , 2004, IEEE International Conference on Robotics and Automation, 2004. Proceedings. ICRA '04. 2004.

[2]  Tao Mei,et al.  A networked smart sensor system for gripper of robots , 2002, 2nd ISA/IEEE Sensors for Industry Conference,.

[3]  Kazuo Machida,et al.  Precise space telerobotic system using 3-finger multisensory hand , 1995, Proceedings of 1995 IEEE International Conference on Robotics and Automation.

[4]  Cheng Li,et al.  Dynamic decoupling and compensating methods of multi-axis force sensors , 2000, IEEE Trans. Instrum. Meas..

[5]  Tao Mei,et al.  Feature-level data fusion of a robotic multisensor gripper using ANN , 2001, Other Conferences.

[6]  Tao Mei,et al.  Estimation of wrist force/torque using data fusion of finger force sensors , 2004 .

[7]  Tao Mei,et al.  Measurement of wrist force/torque using data fusion technique , 2004, 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE Cat. No.04CH37566).