物体の変形特性に依存しない人とロボットの協調搬送フレームワーク
An Object Deformation-Agnostic Framework for Human-Robot Collaborative Transportation
物体の変形度合いに関わらず、人間の動作意図を検出して移動ロボットが全身反応動作で協調搬送するフレームワークを提案し、剛体からロープまで対応可能なことを示した。
著者: Doganay Sirintuna, Alberto Giammarino, Arash Ajoudani
分類: cs.RO
原文アブストラクト
In this study, an adaptive object deformability-agnostic human-robot collaborative transportation framework is presented. The proposed framework enables to combine the haptic information transferred through the object with the human kinematic information obtained from a motion capture system to generate reactive whole-body motions on a mobile collaborative robot. Furthermore, it allows rotating the objects in an intuitive and accurate way during co-transportation based on an algorithm that detects the human rotation intention using the torso and hand movements. First, we validate the framework with the two extremities of the object deformability range (i.e, purely rigid aluminum rod and highly deformable rope) by utilizing a mobile manipulator which consists of an Omni-directional mobile base and a collaborative robotic arm. Next, its performance is compared with an admittance controller during a co-carry task of a partially deformable object in a 12-subjects user study. Quantitative and qualitative results of this experiment show that the proposed framework can effectively handle the transportation of objects regardless of their deformability and provides intuitive assistance to human partners. Finally, we have demonstrated the potential of our framework in a different scenario, where the human and the robot co-transport a manikin using a deformable sheet.
