arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.00460cs.ROcs.AI
收藏

从运动动觉到物体属性:人类注意力的在线识别

From Movement Kinematics to Object Properties: Online Recognition of Human Carefulness

Italian Institute of Technology(意大利技术研究院);University of Genoa(热那亚大学)

Linda Lastrico, Alessandro Carfì, Francesco Rea, Alessandra Sciutti, Fulvio Mastrogiovanni

摘要:

在操纵物体时,人类会根据所处理物体的特性来调整自己的动作。因此,一个细心的观察者可以预见被操纵物体的隐藏属性,如它的重量,温度,甚至它是否需要特别小心的操作。这项研究是朝着赋予人形机器人这最后一种能力迈出的一步。具体来说,我们研究了机器人如何仅从视觉在线推断人类伙伴在移动物体时是否小心。我们证明了一个人形机器人可以执行这种推理,即使在低分辨率的相机具有高精度(高达81.3%)。只有在没有障碍物的短距离移动中,谨慎识别是不够的。通过观察伙伴的动作来迅速识别运动的谨慎性,将允许机器人调整其对物体的动作,以显示与人类伙伴相同的照顾程度。

英文摘要:

When manipulating objects, humans finely adapt their motions to the characteristics of what they are handling. Thus, an attentive observer can foresee hidden properties of the manipulated object, such as its weight, temperature, and even whether it requires special care in manipulation. This study is a step towards endowing a humanoid robot with this last capability. Specifically, we study how a robot can infer online, from vision alone, whether or not the human partner is careful when moving an object. We demonstrated that a humanoid robot could perform this inference with high accuracy (up to 81.3%) even with a low-resolution camera. Only for short movements without obstacles, carefulness recognition was insufficient. The prompt recognition of movement carefulness from observing the partner's action will allow robots to adapt their actions on the object to show the same degree of care as their human partners.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑