机械臂抓取行为规划研究综述

doi:10.3969/j.issn.1006-2475.2018.09.003

摘要/Abstract

摘要： 随着机器人工作环境越来越复杂，通过对其示范性的教学，可以使机器人更快地适应所处的环境，更好地完成人类所给的任务。在机器人行为中，机械臂在机器人工作中是不可缺少的。近年来，对机械臂抓取行为的建模控制成为科研工作的一个热点。最前沿的方法多从行为获取和行为表征2个方面着手，在行为获取方面大致有2种方法，一种是真人示教法，另一种是虚拟平台示教法；行为表征方面多采用深度学习的方法。本文从数据获取的角度对近几年机械臂建模和控制的研究发展进行综述。

关键词: 机械臂, 建模, 控制, 模仿, 深度学习, 真人示教

Abstract: As the robot’s working environment becomes more and more complex, through exemplary teaching to them, we can make the robot adapt to its environment faster and better accomplish the missions that humans have given. In the robot’s behavior, the robot arm is indispensable in the robot’s work. In recent years, the modeling and control of robotic arm grabbing has become a hot topic in scientific research. The most cutting-edge methods start with behavior acquisition and behavioral representation. There are roughly two methods for behavior acquisition, one is the real-person teaching method, the other is the virtual platform teaching method, and most of the behavioral characterization uses deep learning method. In this paper, the method of data acquisition is used as an example to review the research and development of manipulator modeling and control in recent years.

Key words: robot arm, modeling, control, imitation, deep learning, real-person teaching

中图分类号:

TP24

韩丽丽,王奇志,杨永刚. 机械臂抓取行为规划研究综述[J]. 计算机与现代化, doi: 10.3969/j.issn.1006-2475.2018.09.003.

HAN Li-li, WANG Qi-zhi, YANG Yong-gang. Review of Robot Arm Grasping Behavior Planning[J]. Computer and Modernization, doi: 10.3969/j.issn.1006-2475.2018.09.003.

参考文献

［1］ Yong Y S, Huang Yanjiang, Chiba R, et al. Teaching-playback robot manipulator system in consideration of singularities［C］// Proceedings of the 2013 IEEE/ASME International Conference on Advanced Intelligent Mechatronics. 2013:453-458.
［2］ Lee S H, Li Chengjie, Kim D H, et al. The direct teaching and playback method for robotic deburring system using the adaptiveforce-control［C］// Proceedings of the 2009 IEEE International Symposium on Assembly and Manufacturing. 2009:235-241.
［3］ Choi S, Eakins W, Rossano G, et al. Lead-through robot teaching［C］// Proceedings of the 2013 IEEE Conference on Technologies for Practical Robot Applications. 2013,doi: 10.1109/TePRA.2013.6556347.
［4］ Schaal S. Is imitation learning the route to humanoid robots?［J］. Trends in Cognitive Sciences, 1999,3(6):233-242.
［5］ Calinon S. Robot Programming by Demonstration: A Probabilistic Approach［M］. EPFL Press, 2009.
［6］张利格,毕树生,高金磊. 仿人机器人复杂动作设计中人体运动数据提取及分析方法［J］. 自动化学报, 2010,36(1):107-112.
［7］李少波,赵毅夫,赵群飞,等. 机器人的人体姿态动作识别与模仿算法［J］. 计算机工程, 2013,39(8):181-186.
［8］ Erol A, Bebis G, Nicolescu M, et al. Vision-based hand pose estimation: A review［J］. Computer Vision and Image Understanding, 2007,108(1-2):52-73.
［9］ Mitra S, Acharya T. Gesture recognition: A survey［J］. IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews, 2007,37(3):311-324.
［10］Dewaele G, Devernay F, Horaud R. Hand motion from 3D point trajectories and a smooth surface model［C］// Proceedings of the 2004 European Conference on Computer Vision. 2004:495-507.
［11］Ren Zhou, Yuan Junsong, Meng Jingjing, et al. Robust part-based hand gesture recognition using Kinect sensor［J］. IEEE Transactions on Multimedia, 2013,15(5):1110-1120.
［12］Ibaez R, Soria , Teyseyre A, et al. Easy gesture recognition for Kinect［J］. Advances in Engineering Software, 2014,76:171-180.
［13］Xiao Yang, Zhang Zhijun, Beck A, et al. Human: Robot interaction by understanding upper body gestures［J］. Presence: Teleoperators and Virtual Environments, 2014,23(2):133-154.
［14］Du Guanglong, Zhang Ping. Human-manipulator interface using hybrid sensors with Kalman filters and adaptive multi-space transformation［J］. Measurement, 2014,55:413-422.
［15］Bueno M, Díaz-Vilario L, Martínez-Sánchez J, et al. Metrological evaluation of KinectFusion and its comparison with Microsoft Kinect sensor［J］. Measurement, 2015,73:137-145.
［16］朱特浩,赵群飞,夏泽洋. 利用Kinect的人体动作视觉感知算法［J］. 机器人, 2014,36(6):647-653.
［17］Yavan E, Uar A. Gesture imitation and recognition using Kinect sensor and extreme learning machines［J］. Measurement, 2016,94:852-861.
［18］Wei S E, Ramakrishna V, Kanade T, et al. Convolutional pose machines［C］// Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. 2016:4724-4732.
［19］Cao Zhe, Simon T, Wei S E, et al. Realtime multi-person 2D pose estimation using part affinity fields［C］// Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. 2017:1302-1310.
［20］Simon T, Joo H, Matthews I, et al. Hand keypoint detection in single images using multiview bootstrapping［C］// Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. 2017:4645-4653.
［21］Pokorny F T, Kragic D. Classical grasp quality evaluation: New algorithms and theory［C］// Proceedings of the 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems. 2013:3493-3500.
［22］Bohg J, Morales A, Asfour T, et al. Data-driven grasp synthesis: A survey［J］. IEEE Transactions on Robotics, 2014,30(2):289-309.
［23］Stouraitis T, Hillenbrand U, Roa M A. Functional power grasps transferred through warping and replanning［C］// Proceedings of the 2015 IEEE International Conference on Robotics and Automation. 2015:4933-4940.
［24］Pokorny F T, Hang Kaiyu, Kragic D. Grasp moduli spaces［C］// Proceedings of the 2013 IEEE International Conference on Robotics and Automation. 2013:389-396.
［25］Goldfeder C, Allen P K. Data-driven grasping［J］. Autonomous Robots, 2011,31(1):1-20.
［26］Goldfeder C, Ciocarlie M, Dang Hao, et al. The Columbia grasp database［C］// Proceedings of the 2009 IEEE International Conference on Robotics and Automation. 2009:1710-1716.
［27］Brook P, Ciocarlie M, Hsiao K. Collaborative grasp planning with multiple object representations［C］// Proceedings of the 2011 IEEE International Conference on Robotics and Automation. 2011:2851-2858.
［28］Kehoe B, Matsukawa A, Candido S, et al. Cloud-based robot grasping with the Google object recognition engine［C］// Proceedings of the 2013 IEEE International Conference on Robotics and Automation. 2013:4263-4270.
［29］Detry R, Ek C H, Madry M, et al. Learning a dictionary of prototypical grasp-predicting parts from grasping experience［C］// Proceedings of the 2013 IEEE International Conference on Robotics and Automation. 2013:601-608.
［30］Herzog A, Pastor P, Kalakrishnan M, et al. Learning of grasp selection based on shape-templates［J］. Autonomous Robots, 2014,36(1-2):51-65.
［31］Zhang Li, Ciocarlie M, Hsiao K. Grasp evaluation with graspable feature matching［C］// Proceedings of the 2011 RSS Workshop on Mobile Manipulation: Learning to Manipulate. 2011.
［32］Lenz I, Lee H, Saxena A. Deep learning for detecting robotic grasps［J］. International Journal of Robotics Research, 2015,34(4-5):705-724.
［33］Kappler D, Bohg J, Schaal S. Leveraging big data for grasp planning［C］// Proceedings of the 2015 IEEE International Conference on Robotics and Automation. 2015:4304-4311.
［34］Laskey M, Mahler J, McCarthy Z, et al. Multi-armed bandit models for 2D grasp planning with uncertainty［C］// Proceedings of the 2015 IEEE Conference on Automation Science and Engineering. 2015:572-579.
［35］Mahler J, Pokorny F T, Hou B, et al. Dex-Net 1.0: A cloud-based network of 3D objects for robust grasp planning using a multi-armed bandit model with correlated rewards［C］// Proceedings of the 2016 IEEE International Conference on Robotics and Automation. 2016:1957-1964.
［36］Mahler J, Liang J, Niyaz S, et al. Dex-Net 2.0: Deep Learning to Plan Robust Grasps with Synthetic Point Clouds and Analytic Grasp Metrics［DB/OL］. https://arxiv.org/pdf/1703.09312v3.pdf, 2017-08-08.
［37］Mahler J, Matl M, Liu Xinyu, et al. Dex-Net 3.0: Computing Robust Robot Vacuum Suction Grasp Targets in Point Clouds Using a New Analytic Model and Deep Learning［DB/OL］. https://arxiv.org/pdf/1709.06670v1.pdf,2017-09-19.
［38］Cutler M, How J P. Efficient reinforcement learning for robots using informative simulated priors［C］// Proceedings of the 2015 IEEE International Conference on Robotics and Automation. 2015:2605-2612.
［39］Koos S, Mouret J B, Doncieux S. Crossing the reality gap in evolutionary robotics by promoting transferable controllers［C］// Proceedings of the 12th Annual Conference on Genetic and Evolutionary Computation. 2010:119-126.
［40］Kober J, Bagnell J A, Peters J. Reinforcement learning in robotics: A survey［J］. International Journal of Robotics Research, 2013,32(11):1238-1274.
［41］Cutler M, Walsh T J, How J P. Reinforcement learning with multi-fidelity simulators［C］// Proceedings of the 2014 IEEE International Conference on Robotics and Automation. 2014:3888-3895.
［42］Cully A, Clune J, Tarapore D, et al. Robots that can adapt like animals［J］. Nature, 2015,521(7553):503-507.
［43］Rajeswaran A, Ghotra S,Ravindran B, et al. EPOpt: Learning robust neural network policies using model ensembles［C］// Proceedings of the 2017 International Conference on Learning Representations. 2017.
［44］Christiano P, Shah Z, Mordatch I, et al. Transfer from Simulation to Real World Through Learning Deep Inverse Dynamics Model［DB/OL］. https://arxiv.org/pdf/1610.03518v1.pdf, 2016-10-11.
［45］Hanna J P, Stone P. Grounded action transformation for robot learning in simulation［C］// Proceedings of the 31st AAAI Conference on Articial Intelligence. 2017:3834-3840.
［46］于建均,徐骢驰,阮晓钢,等. 基于神经网络的机械臂的模仿学习研究［J］. 控制工程, 2017(11):2368-2373.
［47］Schulman J, Moritz P, Levine S, et al. High-dimensional Continuous Control Using Generalized Advantage Estimation［DB/OL］. https://arxiv.org/pdf/1506.02438v5.pdf, 2016-09-09.
［48］Rusu A A, Rabinowitz N C, Desjardins G, et al. Progressive Neural Networks［DB/OL］. https://arxiv.org/pdf/1606.04671v3.pdf, 2016-09-07.
［49］Rusu A A, Vecerik M, Rothorl T, et al. Sim-to-real Robot Learning from Pixels with Progressive Nets［DB/OL］.https://arxiv.org/pdf/1610.04286v1.pdf, 2016-10-13.
［50］Rahmatizadeh R, Abolghasemi P, Behal A, et al. From Virtual Demonstration to Real-world Manipulation Using LSTM and MDN［DB/OL］.https://arxiv.org/pdf/1603.03833v4.pdf, 2017-11-22.

[1]	彭宗玉, 黄开启, 苏建华, 王丽丽. 基于无模型自适应控制的视觉伺服[J]. 计算机与现代化, 2024, 0(01): 29-34.
[2]	胡崇佳, 刘金洲, 方立. 基于无监督域适应的室外点云语义分割[J]. 计算机与现代化, 2024, 0(01): 74-79.
[3]	孟娜, 方维维, 路红英. 一种面向微控制器上环境声音分类的DNN压缩方法[J]. 计算机与现代化, 2024, 0(01): 80-86.
[4]	林威. 基于自监督学习和数据回放的新闻推荐模型增量学习方法[J]. 计算机与现代化, 2023, 0(12): 1-6.
[5]	宋涛涛, 李艳萍, 李洪港, 韩春雪. 基于改进变结构趋近律的机械臂滑模控制系统[J]. 计算机与现代化, 2023, 0(12): 14-18.
[6]	梁天恺, 黄康华, 刘凯航, 兰岚, 曾碧. 基于双向同态加密的深度联邦图片分类方法[J]. 计算机与现代化, 2023, 0(12): 36-40.
[7]	邱凯星, 冯广. 基于双重特征注意力的多标签图像分类模型[J]. 计算机与现代化, 2023, 0(12): 41-47.
[8]	杜康, 郭鲁钰, 徐啟蕾, 单宝明, 张方坤. 基于模型种群分析变量选择的红外光谱建模方法[J]. 计算机与现代化, 2023, 0(12): 48-52.
[9]	张伯泉, 麦海鹏, 陈嘉敏, 逄锦聚. 基于高灰度值注意力机制的脑白质高信号分割[J]. 计算机与现代化, 2023, 0(12): 67-75.
[10]	马泽宇, 叶宁, 徐康, 王甦, 王汝传, . 基于FMCW雷达和ResNeSt-GRU的行为识别方法[J]. 计算机与现代化, 2023, 0(11): 101-107.
[11]	李延满, 王必恒, 赵羚焱. 基于轻量化YOLOv5的安全帽检测[J]. 计算机与现代化, 2023, 0(10): 59-64.
[12]	黎世达, 项剑文. 一种提高图像识别模型鲁棒性的弱化强化方法[J]. 计算机与现代化, 2023, 0(10): 70-76.
[13]	韩冬松, 沙乐天, 赵创业. 基于蠕虫和代理的工控系统攻击建模[J]. 计算机与现代化, 2023, 0(10): 107-114.
[14]	沈加炜, 陆一鸣, 陈晓艺, 钱美玲, 陆卫忠, . 基于深度学习的人体行为检测方法研究综述[J]. 计算机与现代化, 2023, 0(09): 1-9.
[15]	刘禅奕, 黄丹, 薛林雁, 王涛, 朱桃, . 改进EfficientNet网络的COVID-19 X光分类[J]. 计算机与现代化, 2023, 0(09): 94-99.