Learning by Breaking: Food Fracture Anticipation for Robotic Food Manipulation

Learning by Breaking: Food Fracture Anticipation for Robotic Food Manipulation
复制标题

通过打破学习:机器人食物操作的食物破裂预期

DOI:
10.1109/access.2022.3207491
复制
发表时间:
2022
期刊:
影响因子:
3.9
通讯作者:
Hashimoto Atsushi
Hashimoto Atsushi
中科院分区:
计算机科学3区
文献类型:
--
作者:
Ishikawa Reina;Hamaya Masashi;Von Drigalski Felix;Tanaka Kazutoshi;Hashimoto Atsushi

文献摘要

参考文献

被引文献

相似文献

这项研究旨在预测机器人食品操作过程中易碎食品的破裂。预测骨折使机器人能够操纵配料,而不会出现不可逆转的失败。食品质构领域研究的食品断裂模型很好地解释了脆性物体的特性。然而,即使在相同的成分中,由于物理性质的差异,它们可能不会直接应用于机器人操作。为此,我们开发了一个带有触觉感知模块和简单的递归神经网络的骨折预测系统。关键的想法是允许机器人在训练过程中打破成分-样本收集。通过简单的信号处理识别骨折的时间,并用于监测。我们用三种典型的易碎食物:豆腐、薯片和香蕉进行了真实的机器人实验。作为实现灵活易碎对象操作的第一步,我们对所提出的方法进行了评估,以用于对象拾取的基本任务。在网上演示中,该方法成功地抓住了没有骨折的易碎食物。在一次离线评估中,该方法通过60次破裂试验,对所有成分的召回率约为80%,从而预测了骨折。我们相信,我们的方法可以用来避免在其他类型的食物处理中发生破碎,例如握住、压紧和滚动。
This study aimed to anticipate fractures of fragile food during robotic food manipulation. Anticipating fractures allows a robot to manipulate ingredients without irreversible failure. Food fracture models investigated in food texture fields explain the properties of fragile objects well. However, they may not directly apply to robot manipulation due to the variance in physical properties even within the same ingredient. To this end, we developed a fracture-anticipation system with a tactile sensing module and a simple recurrent neural network. The key idea was to allow the robot to break ingredients during training-sample collection. The timing of fractures was identified via simple signal processing and used for supervision. We performed real robot experiments with three typical fragile foods: tofu, potato chips, and bananas. As the first step toward flexible fragile-object manipulation, we evaluated the proposed method for the fundamental task of object picking. The method successfully grasped the fragile foods without fractures in an online demonstration. In an offline evaluation, the method predicted the fractures with a recall of approximately 80% for all ingredients with 60 breaking trials. We believe that our method can be used to avoid breakage in other types of food manipulation, e.g., holding, pressing, and rolling.
基于视觉的触觉传感器 FingerVision 的触觉行为
DOI: 10.1142/s0219843619400024
发表时间: 2019
影响因子: 1.5
作者:
Yamaguchi, Akihiko;Atkeson, Christopher G.
通讯作者: Atkeson, Christopher G.
DOI: 10.1007/978-3-030-71151-1_28
发表时间: 2021
期刊: ArXiv
影响因子: --
作者:
A. Sawhney;Steven Lee;Kevin Zhang;M. Veloso;Oliver Kroemer
通讯作者: Oliver Kroemer
高度变形的指尖可实现细腻的抓握
DOI: --
发表时间: 2018
期刊:
影响因子: --
作者:
細川伸也;八方直久;Artoni K. R. Ang;木村耕治;林好一;松下智裕;片山哲,松田佑;Tetsuyou Watanabe
通讯作者: Tetsuyou Watanabe
反式AM
DOI: --
发表时间: --
期刊:
影响因子: --
作者:
通讯作者: --
DOI: 10.1016/j.jfoodeng.2009.11.020
发表时间: 2010-06-01
影响因子: 5.5
作者:
Pettersson, A.;Davis, S.;Ohlsson, T.
通讯作者: Ohlsson, T.