Modeling human-likeness in approaching motions of dual-arm autonomous robots

This paper addresses the problem of obtaining human-like motions with an anthropomorphic dual-arm torso assembled on a mobile platform. The focus is set on the coordinated movements of the robotic arms and the robot base while approaching a table to subsequently perform a bimanual manipulation task. For this, human movements are captured and mapped to the robot in order to compute the human dual-arm synergies. Since the demonstrated synergies change depending on the robot position, a recursive Cartesian-space discretization is presented based on these differences. Thereby, different movements of the arms are assigned to different regions of the Cartesian space. As an application example, a motion-planning algorithm exploiting this information is proposed and used.