Estimation of Care Receiver’s Position Based on Tactile Information for Transfer Assist Using Dual Arm Robot

Abstract

<div class=""abs_img""><img src=""[disp_template_path]/JRM/abst-image/00260006/07.jpg"" width=""300"" />Position estimation by forearms</div> For a robot that uses two arms to lift and transfer a care receiver from a bed to a wheelchair, we report a method of estimating the positioning of the care receiver. The maneuver for such a task involves a high DOF, and the robot is capable of executing the maneuver much like a human being. The care receiver may experience pain or become unstable when being carried, however, depending on the positioning of contact between the robot’s arms and the care receiver. For this reason, nursing care robots must be able to recognize the positioning of contact with the care receiver and either modify it or alert the operator if it is unsuitable. We use the information obtained by tactile sensors on the robot’s arms when making contact with the care receiver to estimate the latter’s positioning. By dividing a care receiver’s position on a bed into nine zones and applying machine learning to tactile sensor data and positioning, it is possible to estimate positioning highly accurately. </span>