arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2211.16693cs.ROcs.AI
收藏

复杂背景下透明物体抓取的视觉-触觉融合

Visual-tactile Fusion for Transparent Object Grasping in Complex Backgrounds

Tsinghua Shenzhen International Graduate School(清华大学深圳国际研究生院);RISC-V International Open Source Laboratory(RISC-V国际开源实验室);Tsinghua-Berkeley Shenzhen Institute(清华-伯克利深圳学院);Institute of Artificial Intelligence, Collaborative Innovation Center for the Marine Artificial Intelligence, Shanghai University(上海大学人工智能学院、海洋人工智能协同创新中心)

Shoujie Li, Haixin Yu, Wenbo Ding, Houde Liu, Linqi Ye, Chongkun Xia, Xueqian Wang, Xiao-Ping Zhang

AI总结:

本文提出视觉-触觉融合框架,结合TGCNN抓取网络、触觉校准与融合分类,在复杂背景下显著提升透明物体抓取成功率和分类准确率。

摘要:

透明物体的准确检测与抓取对机器人而言具有挑战性但意义重大。本文提出了一种面向复杂背景和变化光照条件下透明物体抓取的视觉-触觉融合框架,包括抓取位置检测、触觉校准和基于视觉-触觉融合的分类。首先,提出了一种基于高斯分布数据标注的多场景合成抓取数据集生成方法。此外,提出了一种名为TGCNN的新型抓取网络用于抓取位置检测,在合成场景和真实场景中均表现出良好效果。在触觉校准方面,受人类抓取行为启发,设计了一种基于全卷积网络的触觉特征提取方法和一种基于中心位置的自适应抓取策略,与直接抓取相比成功率提高了36.7%。进一步地,提出了一种用于透明物体分类的视觉-触觉融合方法,使分类准确率提高了34%。所提出的框架协同发挥了视觉与触觉的优势,大幅提升了透明物体的抓取效率。

英文摘要:

The accurate detection and grasping of transparent objects are challenging but of significance to robots. Here, a visual-tactile fusion framework for transparent object grasping under complex backgrounds and variant light conditions is proposed, including the grasping position detection, tactile calibration, and visual-tactile fusion based classification. First, a multi-scene synthetic grasping dataset generation method with a Gaussian distribution based data annotation is proposed. Besides, a novel grasping network named TGCNN is proposed for grasping position detection, showing good results in both synthetic and real scenes. In tactile calibration, inspired by human grasping, a fully convolutional network based tactile feature extraction method and a central location based adaptive grasping strategy are designed, improving the success rate by 36.7% compared to direct grasping. Furthermore, a visual-tactile fusion method is proposed for transparent objects classification, which improves the classification accuracy by 34%. The proposed framework synergizes the advantages of vision and touch, and greatly improves the grasping efficiency of transparent objects.

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。

↑