Can I Pour Into It? Robot Imagining Open Containability Affordance of Previously Unseen Objects via Physical Simulations
Can I Pour Into It? Robot Imagining Open Containability Affordance of Previously Unseen Objects via Physical Simulations
复制标题
我可以倒进去吗？
DOI：
--
复制
发表时间：
2020
影响因子：
5.2
通讯作者：
G. Chirikjian
中科院分区：
文献类型：
--
作者：
Hongtao Wu;G. Chirikjian
开口容器，即，无盖容器是人类生活中重要且普遍存在的一类物品。在这封信中，我们提出了一种新的方法，让机器人通过物理模拟“想象”一个以前看不见的物体的开放包容性启示。机器人使用RGB-D相机自动扫描物体。扫描的3D模型用于开放式可容纳性想象，其通过物理模拟将颗粒滴落到物体上并计算其中保留的颗粒数量来量化开放式可容纳性启示。该量化用于开放式容器与非开放式容器的二元分类（以下称为开放式容器分类）。如果物体被分类为开口容器，则机器人再次使用物理模拟进一步想象倒入物体中，以获得用于真实的机器人自主倾倒的倾倒位置和取向。我们评估我们的方法对开放的容器分类和自主倾倒的粒状材料的数据集包含130个以前看不见的对象与57个对象类别。虽然我们提出的方法只使用11个对象进行模拟校准，但其开放容器分类与人类判断一致。此外，我们的方法赋予机器人自主倒入数据集中的55个容器的能力，成功率非常高。我们还比较了深度学习方法。结果表明，我们的方法在开放容器分类上实现了与深度学习方法相同的性能，并且在自主倾倒方面优于深度学习方法。此外，我们的方法是完全可以解释的。
Open containers, i.e., containers without covers, are an important and ubiquitous class of objects in human life. In this letter, we propose a novel method for robots to “imagine” the open containability affordance of a previously unseen object via physical simulations. The robot autonomously scans the object with an RGB-D camera. The scanned 3D model is used for open containability imagination which quantifies the open containability affordance by physically simulating dropping particles onto the object and counting how many particles are retained in it. This quantification is used for open-container vs. non-open-container binary classification (hereafter referred to as open container classification). If the object is classified as an open container, the robot further imagines pouring into the object, again using physical simulations, to obtain the pouring position and orientation for real robot autonomous pouring. We evaluate our method on open container classification and autonomous pouring of granular material on a dataset containing 130 previously unseen objects with 57 object categories. Although our proposed method uses only 11 objects for simulation calibration, its open container classification aligns well with human judgements. In addition, our method endows the robot with the capability to autonomously pour into the 55 containers in the dataset with a very high success rate. We also compare to a deep learning method. Results show that our method achieves the same performance as the deep learning method on open container classification and outperforms it on autonomous pouring. Moreover, our method is fully explainable.