Force-Torque Sensor Disturbance Observer using Deep Learning

Abstract

Robots executing force controlled tasks require accurate perception of the applied force in order to guarantee safety. However, dynamic motions generate non-contact forces due to inertial forces. These non-contact forces can be regarded as disturbances to be removed such that only forces generated by contacts with the environment remain. This paper presents an observer based on recurrent neural networks that estimates the non-contact forces measured by a force-torque sensor attached at the end-effector of a robotic arm. The recurrent neural network observer uses signals from the joint encoders of the robotic arm and a low-cost inertial measurement unit to estimate the wrenches (i.e. forces and torques) generated due to gravity, inertia, centrifugal and Coriolis forces. The accuracy of the proposed observer is experimentally evaluated using a force-torque sensor attached to the end-effector of a seven degrees of freedom arm.