Human Intention Estimation With Tactile Sensors in Human-Robot Collaboration

Abstract

In this paper, machine learning methods are proposed for human intention estimation based on the change of force distribution on the interaction surface during human-robot collaboration (HRC). The force distribution under different human intentions are examined when the human and robot are jointly carrying the same piece of object. A pair of Robotiq tactile sensors is applied to monitor the change of force distribution on the interaction surface. Three machine learning algorithms are tested on recognition of human intentions based on the force distribution patterns on the contact surface of grippers for the manipulator. The K-nearest Neighbor model is selected to build a real-time framework, which includes human intention estimation and cooperative motion planning for the robot manipulator. A real-time experiment is conducted to validate the method, which suggests the human intention estimation approach can help enhance the efficiency of HRC.