Tire Pose Estimation and Robotic Depalletizing Method Integrating Covariance Analysis and Random Sample Consensus

doi:10.3901/JME.260324

Abstract

Abstract: In the automotive industry, the depalletizing process for tire assemblies presents several challenges. The workpieces are heavy, and the process demands strict timing and stability requirements. Additionally, the floating positioning of the workpieces makes it difficult to achieve efficient automation through traditional robot teaching methods. Current mainstream approaches, such as manual depalletizing and overhead crane-assisted handling, suffer from low automation levels. Manual depalletizing, while meeting timing requirements, involves high labor intensity and costs, along with short-term risks of falling materials and long-term occupational hazards. To address these issues, an automated depalletizing method is proposed for tire assemblies using industrial robots and a structured light 3D camera for spatial pose recognition. The method considers the spatial stacking of tire assemblies and their pallets, as well as the specific requirements of the depalletizing process. It includes a point cloud measurement and data preprocessing procedure to ensure data integrity and computational accuracy. Since tire surfaces are not simple parametric models, the method refines point cloud boundaries by analyzing their geometric features, calculating covariance matrices, and applying normal vector filtering. A spatial pose calculation process is also designed to meet the automation needs of the depalletizing operation. We built an experimental platform using industrial robots and area-structured light 3D camera to implement the proposed measurement, calculation and depalletizing methods. Repeated tests confirmed the effectiveness of the spatial pose recognition approach in automating the tire assembly depalletizing process. The results demonstrate a 100% recognition accuracy, a repeatability precision of less than ±5 mm, an average algorithm processing time under 1.2 s for multiple tires in single layer, and a total cycle time (including measurement, computation, and robot depalletizing) of less than 13 s per workpiece. The experimental results indicate that the proposed method achieves significant improvements in efficiency, labor cost reduction, and safety risk mitigation compared to traditional approaches.

Key words: industrial robots, area-structured light, automated depalletizing

CLC Number:

TP273

WANG Huiqiang, LI Xiangfei, ZHAO Huan, LI Nan, YUAN Guanzhe, DING Han. Tire Pose Estimation and Robotic Depalletizing Method Integrating Covariance Analysis and Random Sample Consensus[J]. Journal of Mechanical Engineering, 2026, 62(15): 324-333.

Add to citation manager EndNote|Reference Manager|ProCite|BibTeX|RefWorks

URL: http://www.cjmenet.com.cn/EN/10.3901/JME.260324

http://www.cjmenet.com.cn/EN/Y2026/V62/I15/324

References

[1] CANNY J. A computational approach to edge detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence，1986(6)：679-698.
[2] DUDA R O，HART P E. Use of the Hough transformation to detect lines and curves in pictures[J]. Communications of the ACM，1972，15(1)：11-15.
[3] LOWE D G. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision，2004，60：91-110.
[4] DALAL N，TRIGGS B. Histograms of oriented gradients for human detection[C]// 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05). IEEE，2005，1：886-893.
[5] VIOLA P，JONES M. Rapid object detection using a boosted cascade of simple features[C]// Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001. IEEE，2001：I-I.
[6] GIRSHICK R，DONAHUE J，DARRELL T，et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2014：580-587.
[7] REN S，HE K，GIRSHICK R，et al. Faster r-cnn：Towards real-time object detection with region proposal networks[J]. Advances in Neural Information Processing Systems，2015(1)：28.
[8] 刘永刚，于丰宁，章新杰，等.基于激光点云与图像融合的3D目标检测研究[J].机械工程学报，2022，58(24)：289-299. LIU Yonggang，YU Fengning，ZHANG Xinjie，et al. Research on 3D object detection based on laser point cloud and image fusion[J]. Journal of Mechanical Engineering，2022，58(24)：289-299.
[9] HE K，GKIOXARI G，DOLLAR P，et al. Mask r-cnn[C]// Proceedings of the IEEE International Conference on Computer Vision，2017：2961-2969.
[10] REDMON J，DIVVALA S，GIRSHICK R，et al. You only look once：Unified，real-time object detection[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2016：779-788.
[11] 薛培林，吴愿，殷国栋，等. 基于信息融合的城市自主车辆实时目标识别[J]. 机械工程学报，2020，56(12)：165-173.
[12] LIU W，ANGUELOV D，ERHAN D，et al. Ssd：Single shot multibox detector[C]// Computer Vision–ECCV 2016：14th European Conference，Amsterdam，The Netherlands，October 11-14，2016，Proceedings，Part I 14，Springer International Publishing，2016：21-37.
[13] RABBANI T，VAN F. Efficient hough transform for automatic detection of cylinders in point clouds[J]. Isprs Wg Iii/3，Iii/4，2005，3：60-65.
[14] HOPPE H，DEROSE T，DUCHAMP T，et al. Surface reconstruction from unorganized points[C]// Proceedings of the 19th Annual Conference on Computer Graphics and Interactive Techniques，1992：71-78.
[15] BESL P J，MCKAY N D. Method for registration of 3-D shapes[J]. Sensor Fusion IV：Control Paradigms and Data Structures. Spie，1992，1611：586-606.
[16] LOWE D G. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision，2004，60：91-110.
[17] JOHNSON A E，HEBERT M. Using spin images for efficient object recognition in cluttered 3D scenes[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence，1999，21(5)：433-449.
[18] RUSU R B，BLODOW N，BEETZ M. Fast point feature histograms (FPFH) for 3D registration[C]// 2009 IEEE International Conference on Robotics and Automation，IEEE，2009：3212-3217.
[19] MARTIN F，ROBERT B. Random sample consensus：A paradigm for model fitting with applications to image analysis and automated cartography[J]. Commun. ACM，1981，24(6)：381-395.
[20] QI R，SU H，MO K，et al. Pointnet：Deep learning on point sets for 3d classification and segmentation[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2017：652-660.
[21] QI R，YI L，SU H，et al. Pointnet++：Deep hierarchical feature learning on point sets in a metric space[J]. Advances in Neural Information Processing Systems，2017(1)：5105-5114.
[22] SHI S，WANG X，LI H. Pointrcnn：3D object proposal generation and detection from point cloud[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2019：770-779.
[23] ZHOU Y，TUZEL O. Voxelnet：End-to-end learning for point cloud based 3D object detection[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2018：4490-4499.
[24] CHEN X，MA H，WAN J，et al. Multi-view 3D object detection network for autonomous driving[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2017：1907-1915.
[25] JIANG J，LUO X，LUO Q，et al. An overview of hand-eye calibration[J]. The International Journal of Advanced Manufacturing Technology，2022，119(1)：77-97.
[26] DANIILIDIS K. Hand-eye calibration using dual quaternions[J]. The International Journal of Robotics Research，1999，18(3)：286-298.
[27] TSAI Y，LENZ K. A new technique for fully autonomous and efficient 3D robotics hand/eye calibration[J]. IEEE Transactions on Robotics and Automation，1989，5(3)：345-358.
[28] PARK C，MARTIN J. Robot sensor calibration：Solving AX= XB on the Euclidean group[J]. IEEE Transactions on Robotics and Automation，1994，10(5)：717-721.
[29] ZHANG Z. A flexible new technique for camera calibration[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence，2002，22(11)：1330-1334.
[30] MINEO C，PIERCE G，SUMMAN R. Novel algorithms for 3D surface point cloud boundary detection and edge reconstruction[J]. Journal of Computational Design and Engineering，2019，6(1)：81-91.