arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2301.05609cs.ROcs.CVcs.LG
收藏

基于深度图像估计形变的软材料协同操作

Co-manipulation of soft-materials estimating deformation from depth images

Institute of Intelligent Industrial Technologies and Systems for Advanced Manufacturing, National Research Council of Italy(意大利国家研究委员会智能工业技术与先进制造研究所)

Giorgio Nicola, Enrico Villagrossi, Nicola Pedrocchi

AI总结:

本文提出一种基于深度图像和DenseNet-121卷积神经网络的数据驱动方法,用于估计人机协同操作软材料时的形变状态,相比骨骼跟踪器方法性能更优且避免了其缺点。

摘要:

人机协同操作软材料(如织物、复合材料和纸张/纸板)是一项具有挑战性的操作,并具有多种重要的工业应用。估计协同操作材料的形变状态是主要挑战之一。可行的方法通过计算人机相对距离来提供间接测量。在本文中,我们开发了一种数据驱动模型,通过卷积神经网络(CNN)从深度图像估计材料的形变状态。首先,我们将材料的形变状态定义为当前机器人位姿与人类抓取位置之间的相对旋转平移。该模型通过卷积神经网络(具体为在ImageNet上预训练的DenseNet-121)估计当前形变状态。当前形变状态与期望形变状态之间的差值被输入机器人控制器,控制器输出扭转指令。本文描述了所开发的获取、预处理数据集和训练模型的方法。该模型与当前基于相机骨骼跟踪器的最先进方法进行了比较。结果表明,我们的方法取得了更好的性能,并避免了使用骨骼跟踪器引起的各种缺点。最后,我们还研究了不同架构和数据集规模下的模型性能,以最小化数据集采集所需的时间。

英文摘要:

Human-robot co-manipulation of soft materials, such as fabrics, composites, and sheets of paper/cardboard, is a challenging operation that presents several relevant industrial applications. Estimating the deformation state of the co-manipulated material is one of the main challenges. Viable methods provide the indirect measure by calculating the human-robot relative distance. In this paper, we develop a data-driven model to estimate the deformation state of the material from a depth image through a Convolutional Neural Network (CNN). First, we define the deformation state of the material as the relative roto-translation from the current robot pose and a human grasping position. The model estimates the current deformation state through a Convolutional Neural Network, specifically a DenseNet-121 pretrained on ImageNet.The delta between the current and the desired deformation state is fed to the robot controller that outputs twist commands. The paper describes the developed approach to acquire, preprocess the dataset and train the model. The model is compared with the current state-of-the-art method based on a skeletal tracker from cameras. Results show that our approach achieves better performances and avoids the various drawbacks caused by using a skeletal tracker.Finally, we also studied the model performance according to different architectures and dataset dimensions to minimize the time required for dataset acquisition

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。

↑