Stereo vision of liquid and particle flow for robot pouring

Stereo vision of liquid and particle flow for robot pouring
复制标题

机器人浇注的液体和颗粒流立体视觉

DOI:
10.1109/humanoids.2016.7803419
复制
发表时间:
2016
期刊:
2016 IEEE-RAS 16th International Conference on Humanoid Robots (Humanoids)
影响因子:
--
通讯作者:
C. Atkeson
C. Atkeson
中科院分区:
--
文献类型:
--
作者:
Akihiko Yamaguchi;C. Atkeson

文献摘要

参考文献

被引文献

相似文献

我们探索立体视觉识别液体和颗粒流作为三维点(点云)。在我们的浇注研究[1]中,我们注意到我们可以使用光流检测来检测液体流动,特别是使用Lucas-Kanade方法[2]。在本文中,我们扩展了这一思想,使我们能够从立体摄像机中重建三维液体流动,以学习流动的动力学模型。这样的动态模型将有助于推理浇注行为。我们演示了我们的方法倒各种材料:水,焦炭,果冻,培养液,奶精粉。结果表明,该方法能够以点云的形式对三维流动进行检测,并且能够捕捉到实际的流动现象。我们还展示了我们的方法在机器人倒灌场景中是有效的。附带视频:https://youtu.be/2oFjVJwXhKs。
We explore stereo vision for recognizing liquid and particle flow as 3D points (a point cloud). In our pouring research [1], we noticed that we could detect liquid flow using optical flow detection, especially with the Lucas-Kanade method [2]. In this paper we extend this idea so that we can reconstruct 3D liquid flow from a stereo camera in order to learn dynamical models of flow. Such dynamical models would be useful to reason about pouring behaviors. We demonstrate our method in pouring various materials: water, coke, jelly, dish liquid, and creamer powder. The results show that our method could detect the 3D flow as a point cloud, and they captured the actual flow phenomenon. We also show that our method works in a robot pouring scenario. Accompanying video: https://youtu.be/2oFjVJwXhKs.
登记。
DOI: 10.1007/978-1-4939-7647-8_1
发表时间: 2018
期刊: Neuromethods
影响因子: --
作者:
Joshi,AnandA
通讯作者: Joshi,AnandA