In order to grasp and transport an object, grip and load forces must be scaled according to the object’s properties (such as weight). To select the appropriate grip and load forces, the object weight is estimated based on experience or, in the case of robots, usually by use of image recognition. We propose a new approach that makes a robot’s weight estimation less dependent on prior learning and, thereby, allows it to successfully grasp a wider variety of objects. This study evaluates whether it is feasible to predict an object’s weight class in a replacement task based on the time series of upper body angles of the active arm or on object velocity profiles. Furthermore, we wanted to investigate how prediction accuracy is affected by (i) the length of the time series and (ii) different cross-validation (CV) procedures. To this end, we recorded and analyzed the movement kinematics of 12 participants during a replacement task. The participants’ kinematics were recorded by an optical motion tracking system while transporting an object, 80 times in total from varying starting positions to a predefined end position on a table. The object’s weight was modified (made lighter and heavier) without changing the object’s visual appearance. Throughout the experiment, the object’s weight (light/heavy) was randomly changed without the participant’s knowledge. To predict the object’s weight class, we used a discrete cosine transform to smooth and compress the time series and a support vector machine for supervised learning from the achieved discrete cosine transform parameters. Results showed good prediction accuracy (up to $$95\%$$ , depending on the CV procedure and the length of the time series). Even at the beginning of a movement (after only 300 ms), we were able to predict the object weight reliably (within a classification rate of $$88-94\%$$ ).

中文翻译：

---

基于运动学预测物体属性

为了抓取和运输物体，必须根据物体的属性（例如重量）调整抓握力和负载力。为了选择适当的抓握力和负载力，需要根据经验估计物体重量，或者对于机器人，通常使用图像识别来估计物体重量。我们提出了一种新方法，可以使机器人的重量估计更少地依赖于先前的学习，从而使其能够成功地抓取更多种类的物体。本研究评估在替换任务中根据主动臂上身角度的时间序列或物体速度分布来预测物体的重量等级是否可行。此外，我们想研究 (i) 时间序列的长度和 (ii) 不同的交叉验证 (CV) 程序如何影响预测准确性。为此，我们记录并分析了 12 名参与者在替换任务期间的运动运动学。光学运动跟踪系统记录了参与者在运输物体时的运动学情况，从不同的起始位置到桌子上预定的最终位置总共 80 次。修改了对象的重量（变轻和变重），但不改变对象的视觉外观。在整个实验过程中，物体的重量（轻/重）在参与者不知情的情况下随机改变。为了预测对象的权重类别，我们使用离散余弦变换来平滑和压缩时间序列，并使用支持向量机根据所实现的离散余弦变换参数进行监督学习。结果显示出良好的预测准确性（高达 $$95\%$$ ，取决于 CV 程序和时间序列的长度）。即使在运动开始时（仅 300 毫秒后），我们也能够可靠地预测物体重量（在 $$88-94\%$$ 的分类率内）。