An approach for implementing power and force limiting in sensorless industrial robots

This paper discusses an approach to limiting the forces applied by an industrial robot manipulator during contact without the use of external sensors. Using a time-invariant dynamic model in combination with Artificial Neural Networks, the current and torque required by each joint for a given trajectory are estimated with satisfactory precision. The estimated electrical current is compared with the actual current provided by the robot controller and stop commands are issued in the case that the exerted forces exceed a user defined threshold. This approach is implemented in the case of a low payload industrial robot and the results of the experiments show that the approach can provide good collision detection and force limiting results.