Abstract
Applying deep neural network models to robot-arm grasping tasks requires the laborious and time-consuming annotation of a large number of representative examples in the training process. Accordingly, this work proposes a two-stage grasping model, in which the first stage employs learning-based template matching (LTM) algorithm for estimating the object position, and a self-rotation learning (SRL) network is then proposed to estimate the rotation angle of the grasping objects in the second stage. The LTM algorithm measures similarity between the feature maps of the search and template images which are extracted by a pre-trained model, while the SRL network performs the automatic rotation and labelling of the input data for training purposes. Therefore, the proposed model does not consume an expensive human-annotation process. The experimental results show that the proposed model obtains 92.6% when testing on 2400 pairs of the template and target images. Moreover, in performing practical grasping tasks on a NVidia Jetson TX2 developer kit, the proposed model achieves a higher accuracy (88.5%) than other grasping approaches on a split of Cornell-grasp dataset.
Similar content being viewed by others
Data availability
Not applicable.
Code availability
Not applicable.
References
Jiang Y, Moseson S, Saxena A (2011) Efficient grasping from rgbd images: Learning using a new rectangle representation. In: IEEE Int Conf Robot Autom (ICRA), pp 3304–3311
Lenz I, Lee H, Saxena A (2015) Deep learning for detecting robotic grasps. Int J Robot Res 34(4–5):705–724
Li CHG, Chang YM (2019) Automated visual positioning and precision placement of a workpiece using deep learning. Int J Adv Manuf Technol 104(9):4527–4538
Morrison D, Corke P, Leitner J (2020) Learning robust, real-time, reactive robotic grasping. Int J Robot Res 39(2–3):183–201
Redmon J, Angelova A (2015) Real-time grasp detection using convolutional neural networks. In: 2015 IEEE Int Conf Robot Autom (ICRA), IEEE, pp 1316–1322
Wang Z, Li Z, Wang B, Liu H (2016) Robot grasp detection using multimodal deep convolutional neural networks. Adv Mech Eng 8(9):1687814016668077
Zhao D, Sun F, Wang Z, Zhou Q (2021) A novel accurate positioning method for object pose estimation in robotic manipulation based on vision and tactile sensors. Int J Adv Manuf Technol 116(9):2999–3010
Elangovan N, Gerez L, Gao G, Liarokapis M (2021) Improving robotic manipulation without sacrificing grasping efficiency: a multi-modal, adaptive gripper with reconfigurable finger bases. IEEE Access 9:83298–83308
Michalos G, Dimoulas K, Mparis K, Karagiannis P, Makris S (2018) A novel pneumatic gripper for in-hand manipulation and feeding of lightweight complex parts–a consumer goods case study. Int J Adv Manuf Technol 97(9):3735–3750
Spiliotopoulos J, Michalos G, Makris S (2018) A reconfigurable gripper for dexterous manipulation in flexible assembly. Inventions 3(1):4
Kokic M, Stork JA, Haustein JA, Kragic D (2017) Affordance detection for task-specific grasping using deep learning. In: 2017 IEEE-RAS 17th Inter Conf Humanoids, IEEE, pp 91–98
Rezapour Lakani S, Rodríguez-Sánchez AJ, Piater J (2019) Towards affordance detection for robot manipulation using affordance for parts and parts for affordance. Auton Robots 43(5):1155–1172
Mahler J, Matl M, Liu X, Li A, Gealy D, Goldberg K (2018) Dex-net 3.0: Computing robust vacuum suction grasp targets in point clouds using a new analytic model and deep learning. In: 2018 IEEE Int Conf Robot Autom (ICRA), IEEE, pp 5620–5627
Monica R, Aleotti J (2020) Point cloud projective analysis for part-based grasp planning. IEEE Robot Autom Lett 5(3):4695–4702
Levine S, Pastor P, Krizhevsky A, Ibarz J, Quillen D (2018) Learning hand-eye coordination for robotic grasping with deep learning and large-scale data collection. Int J Robot Res 37(4–5):421–436
Pinto L, Gupta A (2016) Supersizing self-supervision: Learning to grasp from 50k tries and 700 robot hours. In: 2016 IEEE Int Conf Robot Autom (ICRA), IEEE, pp 3406–3413
Le MT, Lien JJJ (2021) Learning-based template matching for robot arm grasping. In: 2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC), IEEE, pp 1763–1768
Chen F, Ye X, Yin S, Ye Q, Huang S, Tang Q (2019) Automated vision positioning system for dicing semiconductor chips using improved template matching method. Int J Adv Manuf Technol 100(9):2669–2678
Zhong F, He S, Li B (2017) Blob analyzation-based template matching algorithm for led chip localization. Int J Adv Manuf Technol 93(1):55–63
Desai BK, Pandya M, Potdar M (2013) Comparison of various template matching techniques for face recognition. Int J Eng Res Dev 8(10):16–18
Loew DG (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vision
Rublee E, Rabaud V, Konolige K, Bradski G (2011) Orb: an efficient alternative to sift or surf. In: IEEE Int Conf Comput Vision, pp 2564–2571
Oron S, Dekel T, Xue T, Freeman WT, Avidan S (2017) Best-buddies similarity–robust template matching using mutual nearest neighbors. IEEE Trans Pattern Anal Machine Intell 40(8):1799–1813
Talmi I, Mechrez R, Zelnik-Manor L (2017) Template matching with deformable diversity similarity. In: Proc Conf Comput Vis Pattern Recognit, pp 175–183
Kat R, Jevnisek R, Avidan S (2018) Matching pixels using co-occurrence statistics. In: Proc Conf Comput Vis Pattern Recognit, pp 1751–1759
Cheng J, Wu Y, AbdAlmageed W, Natarajan P (2019) QATM: Quality-aware template matching for deep learning. In: Proc Conf Comput Vis Pattern Recognit, pp 11553–11562
Karaoguz H, Jensfelt P (2019) Object detection approach for robot grasp detection. In: 2019 IEEE Int Conf Robot Autom (ICRA), IEEE, pp 4953–4959
Asif U, Tang J, Harrer S (2018) Graspnet: an efficient convolutional neural network for real-time grasp detection for low-powered devices. In: IJCAI, pp 4875–4882
Chen T, Kornblith S, Norouzi M, Hinton G (2020) A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning, PMLR, pp 1597–1607
Grill JB, Strub F, Altché F, Tallec C, Richemond P, Buchatskaya E, Doersch C, Avila Pires B, Guo Z, Gheshlaghi Azar M et al (2020) Bootstrap your own latent-a new approach to self-supervised learning. Adv Neural Info Process Syst 33:21271–21284
Feng Z, Xu C, Tao D (2019) Self-supervised representation learning by rotation feature decoupling. In: Proc Conf Comput Vis Pattern Recognit, pp 10364–10374
Li X, Hu X, Qi X, Yu L, Zhao W, Heng PA, Xing L (2021) Rotation-oriented collaborative self-supervised learning for retinal disease diagnosis. IEEE Trans Med Imag
Sandler M, Howard A, Zhu M, Zhmoginov A, Chen LC (2018) Mobilenetv2: Inverted residuals and linear bottlenecks. In: Proc Conf Comput Vis Pattern Recognit, pp 4510–4520
Deng J, Dong W, Socher R, Li LJ, Li K, Fei-Fei L (2009) Imagenet: A large-scale hierarchical image database. In: IEEE Conf Comput Vis Pattern Recognit, IEEE, pp 248–255
Wu Z, Xiong Y, Yu SX, Lin D (2018) Unsupervised feature learning via non-parametric instance discrimination. In: Proc Conf Comput Vis Pattern Recognit, pp 3733–3742
Ester M, Kriegel HP, Sander J, Xu X (1996) A density-based algorithm for discovering clusters in large spatial databases with noise. AAAI Press, pp 226–231
Wu Y, Lim J, Yang MH (2013) Online object tracking: a benchmark. In: Proc Conf Comput Vis Pattern Recognit, pp 2411–2418
Funding
This study was supported in part by the Ministry of Science and Technology (MOST) of Taiwan, R.O.C., under Grant No. MOST 110-2221-E-006-179. The additional support provided by Tongtai Machine & Tool Co., Ltd. (Taiwan) and Contrel Technology Co., Ltd. (Taiwan) is also gratefully acknowledged.
Author information
Authors and Affiliations
Contributions
All authors contributed to the study conception and design. Material preparation, data collection, analysis, and writing—original draft preparation were performed by Minh-Tri Le; supervision, project administration, writing—review and editing were performed by Jenn-Jier James Lien. All authors read and approved the final manuscript.
Corresponding author
Ethics declarations
Ethics approval
The authors state that the present work is in compliance with the ethical standards.
Consent to participate
There is no consent to participate needed in the present study.
Consent for publication
There is no consent to publish needed in the present study.
Conflicts of interest
The authors declare no competing interests.
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary information
Below is the link to the electronic supplementary material.
Supplementary file23 (MP4 23266 KB)
Rights and permissions
About this article
Cite this article
Le, MT., Lien, JJ.J. Robot arm grasping using learning-based template matching and self-rotation learning network. Int J Adv Manuf Technol 121, 1915–1926 (2022). https://doi.org/10.1007/s00170-022-09374-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00170-022-09374-y