基于视觉感知和触觉先验知识学习的机器人稳定抓取

doi:10.13973/j.cnki.robot.200040

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (781 KB) HTML ( ) 输出: BibTeX \| EndNote (RIS)
引用本文:
薛腾, 刘文海, 潘震宇, 王伟明. 基于视觉感知和触觉先验知识学习的机器人稳定抓取[J]. 机器人, 2021, 43(1): 1-8.DOI: 10.13973/j.cnki.robot.200040. XUE Teng, LIU Wenhai, PAN Zhenyu, WANG Weiming. Stable Robotic Grasp Based on Visual Perception and Prior Tactile Knowledge Learning. ROBOT, 2021, 43(1): 1-8. DOI: 10.13973/j.cnki.robot.200040.

摘要针对机器人抓取过程中需要实时评估抓取质量以动态调整抓取构型的问题，提出了基于触觉先验知识的机器人稳定抓取方法．首先，根据抓取过程中物体抵抗外界扰动的能力，提出了一种基于触觉信息的抓取质量评估方法．在此基础上，建立了视触觉联合数据集并学习触觉先验知识．其次，提出了融合视觉图像和触觉先验知识的稳定抓取构型生成方法．最后，在搭建的机器人抓取系统中对10种目标物体进行了实验验证．结果表明，相比传统的视觉方法，该方法的抓取稳定性提高了55%；针对已知物体和未知物体，稳定抓取成功率分别为86%和79%，体现了较好的泛化效果．

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	薛腾
	刘文海
	潘震宇
	王伟明

关键词 ：稳定抓取, 触觉先验知识, 视触觉融合, 抓取质量评估

Abstract：Considering the problem that the robot needs to estimate the grasp quality in real time to dynamically adjust the grasp configuration in grasping process, a stable robotic grasp method based on prior tactile knowledge learning is proposed. Firstly, a tactile information based method is put forward for evaluating grasp quality according to the capacity of resisting the external perturbations in grasping process. Based on it, a visual-tactile joint dampest is built, and the prior tactile knowledge is learned. Secondly, an architecture is proposed to generate stable grasp configurations by fusing the visual image and the prior tactile knowledge. Finally, an experimental verification with 10 kinds of objects is carried out on the proposed robotic grasp system. The results show that the grasp stability is improved by 55% with the proposed method over traditional vision-based methods, and the success rates of stable grasp are 86% and 79% respectively on known and unknown objects, demonstrating good generalization performance of the proposed method.

Key words： stable grasp prior tactile knowledge visual tactile fusion grasp quality evaluation

收稿日期: 2020-02-16 录用日期: 2020-03-17

TP242

基金资助:国家自然科学基金（51675329， 51675342， 51975350）；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）；上海市工业强基专项资金（GYQJ-20118-1-13）．

通讯作者: 王伟明,wangweiming@sjtu.edu.cn E-mail: wangweiming@sjtu.edu.cn

作者简介: 薛腾(1994-),男,硕士生.研究领域:机器人灵巧操作,多模态融合.
刘文海(1991-),男,博士生.研究领域:机器人抓取,深度学习.
潘震宇(1994-),男,博士生.研究领域:人机协作,力位控制.

链接本文:

https://robot.sia.cn/CN/10.13973/j.cnki.robot.200040 或 https://robot.sia.cn/CN/Y2021/V43/I1/1

[1] 李宇飞,高朝辉,申麟. 基于视觉的机械臂空间目标抓取策略研究[J].中国科学:技术科学, 2015, 45(1):31-35. Li Y F, Gao Z H, Shen L. Study of vision-based space target capturing strategy for manipulators[J]. Scientia Sinica:Technologica, 2015, 45(1):31-35.
[2] Saxena A, Driemeyer J, Ng A Y. Robotic grasping of novel objects using vision[J]. International Journal of Robotics Research, 2008, 27(2):157-173.
[3] Calandra R, Owens A, Upadhyaya M, et al. The feeling of success:Does touch sensing help predict grasp outcomes[DB/OL]. (2017-10-16)[2020-02-01]. https://arxiv.org/abs/1710.05512.
[4] Dang H, Allen P K. Stable grasping under pose uncertainty using tactile feedback[J]. Autonomous Robots, 2014, 36(4):309330.
[5] Hogan F R, Bauza M, Canal O, et al. Tactile regrasp:Grasp adjustments via simulated tactile transformations[C]//IEEE/RSJ International Conference on Intelligent Robots and Systems. Piscataway, USA:IEEE, 2018:2963-2970.
[6] Howe R D, Cutkosky M R. Sensing skin acceleration for slip and texture perception[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA:IEEE, 1989:145150.
[7] Melchiorri C. Slip detection and control using tactile and force sensors[J]. IEEE/ASME Transactions on Mechatronics, 2000, 5(3):235-243.
[8] Su Z, Hausman K, Chebotar Y, et al. Force estimation and slip detection/classification for grip control using a biomimetic tactile sensor[C]//IEEE-RAS International Conference on Humanoid Robots. Piscataway, USA:IEEE, 2015:297-303.
[9] Chebotar Y, Hausman K, Su Z, et al. Self-supervised regrasping using spatio-temporal tactile features and reinforcement learning[C]//IEEE/RSJ International Conference on Intelligent Robots and Systems. Piscataway, USA:IEEE, 2016:19601966.
[10] James J W, Pestell N, Lepora N F. Slip detection with a biomimetic tactile sensor[J]. IEEE Robotics and Automation Letters, 2018, 3(4):3340-3346.
[11] Yuan W, Li R, Srinivasan M A, et al. Measurement of shear and slip with a GelSight tactile sensor[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA:IEEE, 2015:304-311.
[12] Hyttinen E, Kragic D, Detry R. Estimating tactile data for adaptive grasping of novel objects[C]//IEEE-RAS International Conference on Humanoid Robotics. Piscataway, USA:IEEE, 2017:643-648.
[13] Guo D, Sun F C, Liu H P, et al. A hybrid deep architecture for robotic grasp detection[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA:IEEE, 2017:1609-1614.
[14] Goodale M A. Vision and action:The control of grasping[M]. Bristol, UK:Intellect Books, 1990.
[15] Chebotar Y, Hausman K, Su Z, et al. BiGS:BioTac grasp stability dataset[C]//ICRA 2016 Workshop on Grasping and Manipulation Datasets. 2016.
[16] Luo S, Yuan W, Adelson E, et al. ViTac:Feature sharing between vision and tactile sensing for cloth texture recognition[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA:IEEE, 2018:2722-2727.
[17] Wang T, Yang C, Kirchner F, et al. Multimodal grasp data set:A novel visual-tactile data set for robotic manipulation[J]. International Journal of Advanced Robotic Systems, 2019, 16(1). DOI:10.1177/1729881418821571.
[18] He K M, Zhang X Y, Ren S Q, et al. Deep residual learning for image recognition[C]//IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, USA:IEEE, 2016:770-778.
[19] Zeng A, Song S, Yu K T, et al. Robotic pick-and-place of novel objects in clutter with multi-affordance grasping and cross-domain image matching[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA:IEEE, 2018:3750-3757.
[20] Jiang Y, Moseson S, Saxena A. Efficient grasping from RGBD images:Learning using a new rectangle representation[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA:IEEE, 2011:3304-3311.