Path Recognition and Virtual Guides Design for Path Following Based on Human–Robot Collaboration

Abstract

This article presents a path recognition and virtual guides (VGs) design method for a task of path following based on human–robot collaboration. First, a support vector machine combined with least squares is developed to recognize the desired path based on human guidance. Second, VGs are designed based on the admittance control for human–robot collaborative path following, which combine the human's decision-making with the robot's accurate execution capability. The effectiveness and the robustness of the proposed method are verified on a 7-DOF Sawyer robot equipped with a force/torque sensor.