A User-Intention Based Adaptive Manual Guidance with Force-Tracking Capabilities Applied to Walk-Through Programming for Industrial Robots

Abstract

The paper describes a manual guidance controller with force-tracking requirements to perform human-robot interaction tasks. The developed method allows to (i) manually perform the free-motion manipulator positioning along free-motion Cartesian task direction(s), while (ii) perform force-tracking along constrained Cartesian task direction(s). In (i) the set-point of the impedance control is set in real-time for manual guidance purposes defining a variable set-point deformation law for fine or large robot positioning. In (ii) the set-point of the impedance control is set in real-time for force-tracking purposes implementing an impedance force-tracking control law. A rule has been defined to activate/de-activate the force-tracking controller (i.e., to define constrained directions). The proposed control method has been applied to a walk-through programming application, to teach a force-tracking task (a polishing-like task) to an industrial manipulator (a UR10 manipulator has been used as test platform). The teaching phase highlights the achieved behaviors both along free-motion direction(s) and the force-tracking direction(s). The execution phase highlights the proper autonomous execution of the learned task by the robot.