基于图像实例分割的机器人箱体拆垛方法

doi:10.3778/j.issn.1002-8331.2301-0163

摘要/Abstract

摘要： 为了解决工业箱体包裹拆垛任务中传统特征提取方法依赖于箱体形状，难适用于规格多变、混箱垛型的问题，提出一种基于图像实例分割的机器人拆垛方法。为获得准确箱体拣选中心，首先利用Mask R-CNN进行实例分割获得箱体掩膜和分类信息，并在特征提取后添加空间变换网络（spatial transformation network，STN）模块，优化对旋转目标的识别；然后求解掩膜最小外接矩形并后处理获得待拣选箱体像素中心和水平旋转角度，并结合一种拆垛策略进行先行后列排序以确定拣选顺序；最后利用标定方法完成箱体定位，并对规格多变、混箱垛型进行分割和机器人拆垛实验，结果表明，待拆箱体像素中心平均像素距离约4个像素点，空间定位平均误差约1?cm，定位精度满足工业拆垛实际需求。

关键词: 实例分割, Mask R-CNN, 分类, 标定, 工业拆垛

Abstract: In order to solve the problem that the traditional feature extraction method in the unstacking task of industrial box parcels depends on the shape of the box and is difficult to apply to variable specifications and mixed box types, a robot unstacking method based on image instance segmentation is proposed. In order to obtain accurate box picking center, the Mask R-CNN is used to perform instance segmentation to obtain the box mask and classification information, and an STN (spatial transformation network) module is added after feature extraction to optimize the recognition of rotating objects. Then, the minimum circumscribed rectangle of the mask is solved and post-processed to obtain the pixel center and horizontal rotation angle of the box to be picked, and a unstacking strategy is combined to sort first row and then column to determine the picking order. Finally, the calibration method is used to complete the box positioning, and the segmentation and robot unstacking experiments are conducted for variable specifications and mixed box stacking types. The results show that the average pixel distance between the pixel centers of the unboxed body is about 4 pixels, and the average error of spatial location is about 1?cm. The position accuracy meets the actual needs of industrial depalletization.

Key words: instance segmentation, Mask R-CNN, classification, calibration, industrial depalletization

邹汶材, 刘宝临. 基于图像实例分割的机器人箱体拆垛方法[J]. 计算机工程与应用, 2024, 60(10): 209-216.

ZOU Wencai, LIU Baolin. Robot Box Depalletizing Method Based on Image Instance Segmentation[J]. Computer Engineering and Applications, 2024, 60(10): 209-216.

参考文献

[1] ECHELMEYER W, KIRCHHEIM A, WELLBROCK E. Robotics-logistics: challenges for automation of logistic processes[C]//Proceedings of the 2008 IEEE International Conference on Automation & Logistics, 2008.
[2] CACCAVALE R, ARPENTI P, PADUANO G, et al. A flexible robotic depalletizing system for supermarket logistics[J]. IEEE Robotics and Automation Letters, 2020, 5(3): 4471-4476.
[3] ARPENTI P, CACCAVALE R, PADUANO G, et al. RGB-D recognition and localization of cases for robotic depalletizing in supermarkets[J]. IEEE Robotics and Automation Letters Letters, 2020, 5(4): 6233-6238.
[4] KRUG R, STOYANOV T, TINCANI V, et al. The next step in robot commissioning: autonomous picking & palletizing[J]. IEEE Robotics and Automation Letters, 2016, 1(1): 546-553.
[5] 倪鹤鹏, 刘亚男, 张承瑞, 等.基于机器视觉的Delta机器人分拣系统算法[J].机器人, 2016, 38(1): 49-55.
NI H P, LIU Y N, ZHANG C R, et al. Sorting system algorithms based on machine vision for Delta robot[J]. Robot, 2016, 38(1): 49-55.
[6] MAITIN-SHEPARD J, CUSUMANO-TOWNER M, LEI J, et al. Cloth grasp point detection based on multiple-view geometric cues with application to robotic towel folding[C]//Proceedings of the 2010 IEEE International Conference on Robotics and Automation. Piscataway: IEEE, 2010: 2308-2315.
[7] RAMISA A, ALENYA G, MORENO-NOGUER F, et al. Using depth and appearance features for informed robot grasping of highly wrinkled clothes[C]//Proceedings of the 2012 IEEE International Conference on Robotics and Automation. Piscataway: IEEE, 2012: 1703-1708.
[8] JIANG Y, MOSESON S, SAXENA A. Efficient grasping from RGBD images: learning using a new rectangle representation[C]//Proceedings of the 2011 IEEE International Conference on Robotics and Automation. Piscataway: IEEE, 2011: 3304-3311.
[9] KATSOULAS D, KOSMOPOULOS D I. An efficient depalletizing system based on 2D range imagery[C]//Proceedings of the 2001 IEEE International Conference on Robotics & Automation, 2001.
[10] HOLZ D, TOPALIDOU-KYNIAZOPOULOU A, STüCKLER J, et al. Real-time object detection, localization and verification for fast robotic depalletizing[C]//Proceedings of the 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2015.
[11] NAKAMOTO H, ETO H, SONOURA T, et al. High-speed and compact depalletizing robot capable of handling packages stacked complicatedly[C]//Proceedings of the 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2016.
[12] JOCAS M, KURREK P, ZOGHLAMI F, et al. AI-based learning approach with consideration of safety criteria on example of a depalletization robot[C]//Proceedings of the Design Society: International Conference on Engineering Design, 2019: 2041-2050.
[13] FAN X, LIU X, WANG X, et al. An automatic robot unstacking system based on binocular stereo vision[C]//Proceedings of the 2014 International Conference on Security, 2014.
[14] 韩鑫, 余永维, 杜柳青.基于改进单次多框检测算法的机器人抓取系统[J].计算机应用, 2020, 40(8): 2434-2440.
HAN X, YU Y W, DU L Q. Robotic grasping system based on improved single shot multibox detector algorithm[J]. Journal of Computer Applications, 2020, 40(8): 2434-2440.
[15] 杜学丹, 蔡莹皓, 鲁涛, 等. 一种基于深度学习的机械臂抓取方法[J].机器人, 2017, 39(6): 820-828.
DU X D, CAI Y H, LU T, et al. A robotic grasping method based on deep learning[J].Robot, 2017, 39(6): 820-828.
[16] 韩兴, 刘晓平, 王刚, 等.基于深度神经网络复杂场景下的机器人拣选方法[J].北京邮电大学学报, 2019, 42(5): 22-28.
HAN X, LIU X P, WANG G, et al. Robotic sorting method in complex scene based on deep neural network[J]. Journal of Beijing University of Posts and Telecommunications, 2019, 42(5): 22-28.
[17] 郑凯, 方春, 袁思邈, 等. Mask R-CNN模型在茄花花期识别中的应用研究[J].计算机工程与应用, 2022, 58(18): 318-326.
ZHENG K, FANG C, YUAN S M, et al. Application of Mask R-CNN model in identification of eggplant flowering period[J]. Computer Engineering and Applications, 2022, 58(18): 318-326.
[18] 王德明, 颜熠, 周光亮, 等.基于实例分割网络与迭代优化方法的3D视觉分拣系统[J].机器人, 2019, 41(5): 637-648.
WANG D M, YAN Y, ZHOU G L, et al. 3D vision-based picking system with instance segmentation network and iterative optimization method[J].Robot, 2019, 41(5): 637-648.
[19] GU W, BAI S, KONG L. A review on 2D instance segmentation based on deep neural networks[J]. Image and Vision Computing, 2022: 104401.
[20] HARIHARAN B, ARBELáEZ P, GIRSHICK R, et al. Simultaneous detection and segmentation[C]//Proceedings of the 13th European Conference on Computer Vision, 2014: 297-312.
[21] FONTANA E, ZAROTTI W, RIZZINI D L. A comparative assessment of parcel box detection algorithms for industrial applications[C]//Proceedings of the 2021 European Conference on Mobile Robots, 2021.
[22] HE K M, GKIOXARI G, DOLLAR P, et al. Mask R-CNN[C]//Proceedings of the 2017 IEEE International Conference on Computer Vision. Piscataway: IEEE, 2017: 2980-2988.
[23] JADERBERG M, SIMONYAN K, ZISSERMAN A. Spatial transformer networks[C]//Proceedings of the 29th Annual Conference on Neural Information Processing Systems, 2015: 2017-2025.
[24] ZHANG Z. A flexible new technique for camera calibration[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(11): 1330-1334.
[25] 杨尚昆, 王岩松, 郭辉, 等.基于一阶径向畸变算法的双目摄像机多位姿标定方法[J].计算机应用, 2018, 38(9): 2655-2659.
YANG S K, WANG Y S, GUO H, et al. Binocular camera multi-pose calibration method based on radial alignment constraint algorithm[J]. Journal of Computer Applications, 2018, 38(9): 2655-2659.
[26] 杨广林, 孔令富, 王洁.一种新的机器人手眼关系标定方法[J].机器人, 2006, 28(4): 400-405.
YANG G L, KONG L F, WANG J. A new calibration approach to hand-eye relation of manipulator[J]. Robot, 2006, 28(4): 400-405.
[27] GIRSHICK R. Fast R-CNN[C]//Proceedings of the 2015 IEEE International Conference on Computer Vision, 2015: 1440-1448.