Abstract
Within the concept of “Industry 4.0”, one of the fundamental pillars is the concept of intelligent manufacturing. This type of manufacturing demands a high level of adaptability to design changes, greater flexibility in the adjustment of processes and an intensive use of digital information to improve them, being advanced robotics one of the key technologies to achieve this goal.
Classical industrial robotics is evolving towards another production model, which demands the rapid reconfiguration of robotic installations to manufacture different and varied products in smaller batches. In a production environment where flexibility and readjustment to the manufacture of new products must be carried out quickly, one of the fundamental tasks to be accomplished in robotics to reach these objectives efficiently is Bin Picking.
The problem of Bin Picking is one of the basic problems in artificial vision applied to robotics, and although there are numerous research studies related to this problem, it is difficult to seek the adaptability of the solutions provided to a real environment.
The present research work presents a new procedure for the solution of the Bin Picking problem, of quick configuration and execution based on artificial intelligence and point cloud processing.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Miyajima, R.: Deep learning triggers a new era in industrial robotics. IEEE Multimed. 24, 91–96 (2017). https://doi.org/10.1109/MMUL.2017.4031311
Wada, K., Murooka, M., Okada, K., Inaba, M.: 3D object segmentation for shelf bin picking by humanoid with deep learning and occupancy voxel grid map. IEEE-RAS International Conference on Humanoid Robots, pp. 1149–1154 (2016). https://doi.org/10.1109/HUMANOIDS.2016.7803415
Griffiths, D., Boehm, J.: A review on deep learning techniques for 3D sensed data classification. Remote Sens. 11 (2019). https://doi.org/10.3390/rs11121499
Periyasamy, A.S., Schwarz, M., Behnke, S.: Robust 6D object pose estimation in cluttered scenes using semantic segmentation and pose regression networks. In: IEEE International Conference on Intelligent Robots and Systems, pp. 6660–6666 (2018). https://doi.org/10.1109/IROS.2018.8594406
Doumanoglou, A., Kouskouridas, R., Malassiotis, S., Kim, T.-K.: 6D object detection and next-best-view prediction in the crowd (2015). https://doi.org/10.1109/CVPR.2016.390
Schwarz, M., Behnke, S.: PointNet deep learning for RGB-D object perception in cluttered bin picking. In: IEEE International Conference on Robotics and Automation, pp. 2–4 (2017). https://doi.org/10.1109/3DV.2016.68
Schwarz, M., et al.: NimbRo picking: versatile part handling for warehouse automation. In: Proceedings of the IEEE International Conference on Robotics and Automation, pp. 3032–3039 (2017). https://doi.org/10.1109/ICRA.2017.7989348
Lin, C.M., Tsai, C.Y., Lai, Y.C., Li, S.A., Wong, C.C.: Visual object recognition and pose estimation based on a deep semantic segmentation network. IEEE Sens. J. 18, 9370–9381 (2018). https://doi.org/10.1109/JSEN.2018.2870957
Dong, Z., et al.: PPR-Net: point-wise pose regression network for instance segmentation and 6D pose estimation in bin-picking scenarios, pp. 1773–1780 (2020). https://doi.org/10.1109/iros40897.2019.8967895
Blank, A., et al.: 6DoF pose-estimation pipeline for texture-less industrial components in bin picking applications. In: Proceedings 2019 European Conference on Mobile Robots ECMR 2019, pp. 1–7 (2019). https://doi.org/10.1109/ECMR.2019.8870920
Sock, J., Kim, K.I., Sahin, C., Kim, T.K.: Multi-task deep networks for depth-based 6D object pose and joint registration in crowd scenarios. In: British Machine Vision Conference 2018, BMVC 2018, pp. 1–12 (2019)
Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39, 1137–1149 (2017). https://doi.org/10.1109/TPAMI.2016.2577031
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: MobileNetV2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition pp. 4510–4520 (2018). https://doi.org/10.1109/CVPR.2018.00474
Lowe, D.G.: Distinctive image features from scale-invariant keypoints David. Int. J. Comput. Vis. 60(2), 1–28 (2004)
Besl, P., McKay, N.D.: A Method for Registration of 3-D Shapes. IEEE Trans. Pattern Anal. Mach. Intell. 14, 239–256 (1992)
Drost, B., Ulrich, M., Bergmann, P., Hartinger, P., Steger, C.: Introducing MVTec ITODD - a dataset for 3D object recognition in industry. In: Proceedings of the 2017 IEEE International Conference on Computer Vision Workshops (ICCVW) 2017, 2018 Janua, pp. 2200–2208 (2017). https://doi.org/10.1109/ICCVW.2017.257
Murphy, K.P.: Machine Learning - A Probabilistic Perspective - Table-of-Contents. MIT Press (2012). https://doi.org/10.1038/217994a0
Zhang, Z., Sabuncu, M.R.: Generalized cross entropy loss for training deep neural networks with noisy labels. In: Advances in Neural Information Processing Systems 2018, pp. 8778–8788 December 2018 (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Iglesias, A.T., Pastor-López, I., Urquijo, B.S., García-Bringas, P. (2020). Effective Bin Picking Approach by Combining Deep Learning and Point Cloud Processing Techniques. In: de la Cal, E.A., Villar Flecha, J.R., Quintián, H., Corchado, E. (eds) Hybrid Artificial Intelligent Systems. HAIS 2020. Lecture Notes in Computer Science(), vol 12344. Springer, Cham. https://doi.org/10.1007/978-3-030-61705-9_44
Download citation
DOI: https://doi.org/10.1007/978-3-030-61705-9_44
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-61704-2
Online ISBN: 978-3-030-61705-9
eBook Packages: Computer ScienceComputer Science (R0)