机器人抓取对象硬度触觉感知研究

doi:10.3901/JME.2021.23.012

机械工程学报 ›› 2021, Vol. 57 ›› Issue (23): 12-20.doi: 10.3901/JME.2021.23.012

扫码分享

机器人抓取对象硬度触觉感知研究

张宪民^1,2, 王浩楠^1,2, 黄沿江^1,2

1. 华南理工大学广东省精密装备与制造技术重点实验室广州 510641;
2. 华南理工大学机械与汽车工程学院广州 510641

收稿日期:2020-10-14 修回日期:2021-03-21 出版日期:2021-12-05 发布日期:2022-02-28
通讯作者: 黄沿江(通信作者),男,1981年出生,博士,教授,博士研究生导师。主要研究方向为人机共融机器人技术、工业自动化生产线的设计与优化及机电一体化技术。E-mail:mehuangyj@scut.edu.cn
作者简介:张宪民,男,1964年出生,博士,教授,博士研究生导师。主要研究方向为精密定位与精密操作、精密电子装备与现代控制技术、精密并联机器人系统、机电系统的振动与噪声控制等。E-mail:zhangxm@scut.edu.cn;王浩楠,男,1997年出生。主要研究方向为机器人灵巧操作。E-mail:eericwang@163.com
基金资助:
国家自然科学基金（52075178，51820105007，91748111）、广州市基础与应用基础研究（202002030233）和科技部重点研发计划（2020YFB1713400）资助项目。

Research on Robotic Grasping Object Hardness Perception Based on Tactile Sensing

ZHANG Xianmin^1,2, WANG Haonan^1,2, HUANG Yanjiang^1,2

1. Guangdong Key Laboratory of Precision Equipment and Manufacturing Technology, South China University of Technology Guangzhou 510641;
2. School of Mechanical and Automotive Engineering, South China University of Technology, Guangzhou 510641

Received:2020-10-14 Revised:2021-03-21 Online:2021-12-05 Published:2022-02-28

摘要/Abstract

摘要： 物体硬度感知对于机器人进行物体灵巧操作具有重要意义。针对物体硬度感知中传感信号复杂、物体压缩量大而导致的系统鲁棒性差以及容易损伤物体的问题，提出了一种基于触觉传感的机器人抓取对象硬度感知方法。该方法使用两指夹持器轻微挤压物体，通过安装在两指指尖的柔性触觉传感器阵列采集压力序列信号。将压力序列信号进行多项式处理得到非线性特征序列，使用基于决策树的Adaboost算法处理非线性特征序列，实现抓取物体在线硬度等级分类。将基于决策树的Adaboost算法和其他各种算法进行比较，并进行实际物体硬度识别实验。实验结果表明所提方法能够准确实时识别不同抓取对象的硬度。

关键词: 机器人抓取, 硬度感知, 触觉, Adaboost算法

Abstract: The perception of object hardness is of great significance for robots to perform fine manipulation task. Aiming at the problems of poor system robustness and easy damage to objects caused by complex sensing signals and large object compression in object hardness perception, a method of robotic grasping object hardness perception based on tactile sensing is proposed. Pressure sequences are obtained by the flexible tactile sensors when the two fingers gripper slightly squeezes the object. The pressure sequence signals are then polynomial processed to obtain nonlinear characteristics and then input into the Adaboost algorithm which is based on the decision tree to realize online grasped object hardness perception. The Adaboost algorithm is compared with other algorithms, and the hardness perception experiment for novel objects is carried out. Experimental results show that the proposed method can accurately identify the hardness of different grasped objects.

Key words: robotic grasping, hardness perception, tactile, adaboost algorithm

中图分类号:

TG156

张宪民, 王浩楠, 黄沿江. 机器人抓取对象硬度触觉感知研究[J]. 机械工程学报, 2021, 57(23): 12-20.

ZHANG Xianmin, WANG Haonan, HUANG Yanjiang. Research on Robotic Grasping Object Hardness Perception Based on Tactile Sensing[J]. Journal of Mechanical Engineering, 2021, 57(23): 12-20.

参考文献

[1] LEDERMAN S J,KLATZKY R L. Extracting object properties through haptic exploration[J]. Acta Psychologica,1993,84(1):29-40.
[2] KONSTANTINOVA J,COTUGNO G,DASGUPTA P, et al. Palpation force modulation strategies to identify hard regions in soft tissue organs[J]. PLOS ONE,2017,12(2):e0171706.
[3] CARRELLA A,BRENNAN M J,WATERS T P. Static analysis of a passive vibration isolator with quasi-zero-stiffness characteristic[J]. Journal of Sound and Vibration,2007,301(3):678-689.
[4] YAO Bitao,ZHOU Zude,WANG Lihui,et al. Sensorless and adaptive admittance control of industrial robot in physical human-robot interaction[J]. Robotics and Computer-Integrated Manufacturing,2018,51:158-168.
[5] PONRAJ G,KIRTHIKA S K,THAKOR N V,et al. Development of flexible fabric based tactile sensor for closed loop control of soft robotic actuator[C]//201713th IEEE Conference on Automation Science and Engineering (CASE),China:IEEE,2017:1451-1456.
[6] BEKIROGLU Y,KRAGIC D,KYRKI V. Learning grasp stability based on tactile data and HMMs[C]//19th International Symposium in Robot and Human Interactive Communication,Viareggio:IEEE,2010:132-137.
[7] SATO K,KAMIYAMA K,KAWAKAMI N,et al. Finger-shaped gelforce:sensor for measuring surface traction fields for robotic hand[J]. IEEE Transactions on Haptics,2009,3(1):37-47.
[8] YUAN Wenzhen,DONG Siyuan,ADELSON E H. Gelsight:High-resolution robot tactile sensors for estimating geometry and force[J]. Sensors,2017, 17(12):2762.
[9] PARK J,OH Y,TAN H Z. Effect of cutaneous feedback on the perceived hardness of a virtual object[J]. IEEE Transactions on Haptics,2018,11(4):518-530.
[10] XUE Lingyun,ZHANG Dongfang,CHEN Qingguang,et al. Tactile sensor of hardness recognition based on magnetic anomaly detection[C]//Proceedings of the Young Scientists Forum 2017. International Society for Optics and Photonics,Shanghai:SPIE,2018:107102J.
[11] YUAN Wenzhen,SRINIVASAN M A,ADELSON E H. Estimating object hardness with a GelSight touch sensor[C]//IEEE/RSJ International Conference on Intelligent Robots & Systems. Daejeon:IEEE,2016:208-215.
[12] CHU V,MCMAHON I,RIANO L,et al. Robotic learning of haptic adjectives through physical interaction[J]. Robotics and Autonomous Systems,2015,63:279-292.
[13] DRIMUS A,KOOTSTRA G,BILBERG A,et al. Classification of rigid and deformable objects using a novel tactile sensor[C]//201115th International Conference on Advanced Robotics (ICAR). Tallinn:IEEE,2011:427-434.
[14] BANDYOPADHYAYA I,BABU D,KUMAR A,et al. Tactile sensing based softness classification using machine learning[C]//2014 IEEE International Advance Computing Conference (IACC),Gurgaon:IEEE,2014:1231-1236.
[15] 汪礼超. 基于机械手触觉信息的物体软硬属性识别[D].杭州:浙江大学,2016. WANG Lichao. Recognition of object's softness and hardness based on tactile information of robotic hand[D]. Hangzhou:Zhejiang University,2016.
[16] YUAN Wenzhen,ZHU Chenzhuo,ANDREW O,et al. Shape-independent hardness estimation using deep learning and a gelsight tactile sensor[C]//2017 IEEE International Conference on Robotics and Automation (ICRA),Singapore:IEEE,2017:951-958.
[17] 惠文珊,李会军,陈萌,等. 基于CNN-LSTM的机器人触觉识别与自适应抓取控制[J]. 仪器仪表学报,2019,40(1):211-218. HUI Wenshan,LI Huijun,CHEN Meng,et al. Robotic tactile recognition and adaptive grasping control based on CNN-LSTM[J]. Chinese Journal of Scientific Instrument,2019,40(1):211-218.
[18] BHATTACHARJEE T,REHG J M,KEMP C C. Inferring object properties with a tactile-sensing array given varying joint stiffness and velocity[J]. International Journal of Humanoid Robotics,2018,15(1):1750024.
[19] 张阳阳,黄英,刘月,等. 基于多传感器信息融合的人类抓握特征学习及物体识别[J]. 机器人,2020,42(3):267-277. ZHANG Yangyang,HUANG Ying,LIU Yue,et al. Human grasp feature learning and object recognition based on multi-sensor information fusion[J]. Robot,2020,42(3):267-277.
[20] RICHARDSON B A,KUCHENBECKER K J. Learning to predict perceptual distributions of haptic adjectives[J]. Frontiers in Neurorobotics,2020,13:116.
[21] QIAN Xiaoliang,LI Erkai,ZHANG Jianwei,et al. Hardness recognition of robotic forearm based on semi-supervised generative adversarial networks[J]. Frontiers in Neurorobotics,2019,13:73.
[22] BADER F,RAHIMIFARD S. Challenges for industrial robot applications in food manufacturing[C]//Proceedings of the 2nd International Symposium on Computer Science and Intelligent Control,New York:Association for Computing Machinery,2018:1-8.
[23] BLANES C,MELLADO M,ORTIZ C,et al. Technologies for robot grippers in pick and place operations for fresh fruits and vegetables[J]. Spanish Journal of Agricultural Research,2011,4:1130-1141.
[24] BLUMER A,EHRENFEUCHT A,HAUSSLER D,et al. Occam's razor[J]. Information Processing Letters,1987,24(6):377-380.
[25] HASTIE T,ROSSET S,ZHU J,et al. Multi-class adaboost[J]. Statistics and its Interface,2009,2(3):349-360.
[26] TENZER Y,JENTOFT L P,HOWE R D. Inexpensive and easily customized tactile array sensors using MEMS barometers chips[J]. IEEE R&A Magazine,2012,21(c):2013.
[27] 汪延成,鲁映彤,丁文,等. 柔性触觉传感器的三维打印制造技术研究进展[J]. 机械工程学报,2020,56(19):252-265. WANG Yancheng,LU Yingtong,DING Wen,et al. Recent progress on three-dimensional printing processes to fabricate flexible tactile sensors[J]. Journal of Mechanical Engineering,2020,56(19):252-265.
[28] 罗毅辉,彭倩倩,朱宇超,等. 喷印柔性压力传感器试验研究[J]. 机械工程学报,2019,55(11):90-97. LUO Yihui,PENG Qianqian,ZHU Yuchao,et al. Experimental study of flexible pressure sensor via direct writing[J]. Journal of Mechanical Engineering,2019,55(11):90-97.

机器人抓取对象硬度触觉感知研究

Research on Robotic Grasping Object Hardness Perception Based on Tactile Sensing

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 5

编辑推荐

Metrics

本文评价

[1]	汪延成, 鲁映彤, 丁文, 梅德庆. 柔性触觉传感器的三维打印制造技术研究进展[J]. 机械工程学报, 2020, 56(19): 239-252.
[2]	胡旭晖, 石珂, 祝佳航, 宋爱国. 基于力触觉感知与电刺激反馈的灵巧假手[J]. 机械工程学报, 2019, 55(11): 10-18.
[3]	张友志, 吴海彬, 何可耀, 王浩淼, 叶锦华. 基于双对角匀强电场的柔性触觉传感器研究[J]. 机械工程学报, 2019, 55(10): 17-26.
[4]	唐帮备, 郭钢, 夏进军. 基于用户视/触觉体验的工业设计材质测评方法研究^*[J]. 机械工程学报, 2017, 53(3): 162-172.
[5]	郭卫东;国欣;张玉茹. 2自由度触觉交互装置驱动性能分析[J]. , 2005, 41(8): 75-78.