Surface Tracking with Robot Force Control in Unknown Environment

Abstract

Surface tracking with robot force control for position-controlled robotic manipulator is proposed. A neural network is applied to classify the unknown environment based on its dynamic response of the environment, on-line force feedback data are employed to estimate the normal and tangential directions of the unknown environment, the estimated vectors are used to generate the reference trajectory for the target impedance model. Real-time calculates the curvature of curve to be tracked to adjust the speed of the tangential direction, the reference scaling factor is determined by fuzzy reasoning according to current and forecast contact force, in order to adapt the reference trajectory generated for the changeable environmental parameters and control parameters. Simulation is conducted to verify its force tracking capability.