上海交通大学学报 ›› 2020, Vol. 54 ›› Issue (5): 507-514.doi: 10.16183/j.cnki.jsjtu.2020.05.008

• 学报(中文) • 上一篇    下一篇

基于完备抓取构型和多阶段网络的软体手抓取

刘文海,胡洁,王伟明   

  1. 上海交通大学 机械与动力工程学院, 上海 200240
  • 发布日期:2020-06-02
  • 通讯作者: 胡洁,男,教授,博士生导师,电话(Tel.): 021-34206552; E-mail:hujie@sjtu.edu.cn.
  • 作者简介:刘文海(1991-),男,河南省辉县市人,博士生,研究方向为深度学习和机器人抓取.
  • 基金资助:
    国家自然科学基金项目(51675329,51675342),机械系统与振动国家重点实验室课题(GZ2016KF001,GKZD020018),上海交通大学“医工交叉研究基金”(YG2014MS12),特种车辆及其传动系统智能制造国家重点实验室开放课题(GZ2016KF001)

Soft Gripper Grasping Based on Complete Grasp Configuration and Multi-Stage Network

LIU Wenhai,HU Jie,WANG Weiming   

  1. School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China
  • Published:2020-06-02

摘要: 视觉引导的软体手抓取依赖视觉输出正确的抓取位置、抓取角度和抓取深度,为此提出了面向多手指软体手的完备抓取构型数学模型和多任务损失函数,设计了基于“锚点”旋转框的两阶段深度学习网络,实现了从图像到软体多手指抓取指令的直接映射.通过公开数据库和自建数据库分析了网络模型的性能表现.研究结果表明:多任务损失函数和基于“锚点”旋转框的两阶段网络模型有效提高了多输出抓取检测的准确率和机器人抓取的成功率.最后,构建了机器人软体手抓取系统,抓取实验结果表明:所提方法对视觉定位误差具有一定的抓取稳健性,可成功抓取不同种类的水果,能够达到96%的抓取成功率,对水果皮的抓取也具有很好的泛化能力.

关键词: 软体手;机器人抓取;深度学习;多任务

Abstract: Visual guided robotic grasping of soft gripper depends on correct grasp position, grasp angle and grasp depth, and therefore a complete grasp configuration model and a multi-task loss function for soft gripper are proposed. A two-stage deep learning network based on anchor and rotating blocks is designed to realize direct map from image to multi-gripper grasping. The performance of the network is analyzed by public cornell grasping dataset and self-built dataset. The results show that the two-stage network based on multi-task loss and anchor with rotated blocks improves the accuracy of multi-output grasp detection and increases the success rate of robotic grasping. Finally, the soft robotic grasping system is constructed and the robotic grasping experiment results show that the proposed method provides a certain robustness to vision error, achieves 96% grasp success rate at different fruits, and exhibits a good generalization ability to grasp fruit peel.

Key words: soft gripper; robotic grasping; deep learning; multi-task

中图分类号: