{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,26]],"date-time":"2025-11-26T16:35:55Z","timestamp":1764174955156,"version":"3.37.3"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2021,2,4]],"date-time":"2021-02-04T00:00:00Z","timestamp":1612396800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,2,4]],"date-time":"2021-02-04T00:00:00Z","timestamp":1612396800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100004063","name":"Knut och Alice Wallenbergs Stiftelse","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004063","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Auton Robot"],"published-print":{"date-parts":[[2021,6]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Caging grasps limit the mobility of an object to a bounded component of configuration space. We introduce a notion of partial cage quality based on maximal clearance of an escaping path. As computing this is a computationally demanding task even in a two-dimensional scenario, we propose a deep learning approach. We design two convolutional neural networks and construct a pipeline for real-time planar partial cage quality estimation directly from 2D images of object models and planar caging tools. One neural network, CageMaskNN, is used to identify caging tool locations that can support partial cages, while a second network that we call CageClearanceNN is trained to predict the quality of those configurations. A partial caging dataset of 3811 images of objects and more than 19 million caging tool configurations is used to train and evaluate these networks on previously unseen objects and caging tool configurations. Experiments show that evaluation of a given configuration on a GeForce GTX 1080 GPU takes less than 6 ms. Furthermore, an additional dataset focused on grasp-relevant configurations is curated and consists of 772 objects with 3.7 million configurations. We also use this dataset for 2D Cage acquisition on novel objects. We study how network performance depends on the datasets, as well as how to efficiently deal with unevenly distributed training data. In further analysis, we show that the evaluation pipeline can approximately identify connected regions of successful caging tool placements and we evaluate the continuity of the cage quality score evaluation along caging tool trajectories. Influence of disturbances is investigated and quantitative results are provided.<\/jats:p>","DOI":"10.1007\/s10514-021-09969-6","type":"journal-article","created":{"date-parts":[[2021,2,4]],"date-time":"2021-02-04T16:01:40Z","timestamp":1612454500000},"page":"647-664","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Partial caging: a clearance-based definition, datasets, and deep learning"],"prefix":"10.1007","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3827-3824","authenticated-orcid":false,"given":"Michael C.","family":"Welle","sequence":"first","affiliation":[]},{"given":"Anastasiia","family":"Varava","sequence":"additional","affiliation":[]},{"given":"Jeffrey","family":"Mahler","sequence":"additional","affiliation":[]},{"given":"Ken","family":"Goldberg","sequence":"additional","affiliation":[]},{"given":"Danica","family":"Kragic","sequence":"additional","affiliation":[]},{"given":"Florian T.","family":"Pokorny","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,2,4]]},"reference":[{"key":"9969_CR1","unstructured":"Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., et\u00a0al. (2016). Tensorflow: A system for large-scale machine learning. In Symposium on Operating Systems Design and Implementation (pp. 265\u2013283)."},{"key":"9969_CR2","doi-asserted-by":"crossref","unstructured":"Bicchi, A., & Kumar, V. (2000). Robotic grasping and contact: A review. In Proceedings 2000 ICRA. Millennium conference. IEEE international conference on robotics and automation. Symposia proceedings (Cat. No. 00CH37065) (Vol.\u00a01, pp. 348\u2013353). IEEE.","DOI":"10.1109\/ROBOT.2000.844081"},{"issue":"2","key":"9969_CR3","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1109\/TRO.2013.2289018","volume":"30","author":"J Bohg","year":"2013","unstructured":"Bohg, J., Morales, A., Asfour, T., & Kragic, D. (2013). Data-driven grasp synthesisa survey. IEEE Transactions on Robotics, 30(2), 289\u2013309.","journal-title":"IEEE Transactions on Robotics"},{"key":"9969_CR4","doi-asserted-by":"crossref","unstructured":"Bousmalis, K., Irpan, A., Wohlhart, P., Bai, Y., Kelcey, M., Kalakrishnan, M., et\u00a0al. (2018). Using simulation and domain adaptation to improve efficiency of deep robotic grasping. In IEEE international conference on robotics and automation (ICRA) (Vol. 2018, pp. 4243\u20134250).","DOI":"10.1109\/ICRA.2018.8460875"},{"issue":"11","key":"9969_CR5","first-page":"122","volume":"25","author":"G Bradski","year":"2000","unstructured":"Bradski, G. (2000). The OpenCV library. Dr. Dobb\u2019s Journal of Software Tools, 25(11), 122\u2013125.","journal-title":"Dr. Dobb\u2019s Journal of Software Tools"},{"key":"9969_CR6","unstructured":"Dai, B., & Wipf, D. (2019). Diagnosing and enhancing vae models. arXiv:1903.05789."},{"key":"9969_CR7","doi-asserted-by":"crossref","unstructured":"Gualtieri, M., Ten Pas, A., Saenko, K., & Platt, R. (2016). High precision grasp pose detection in dense clutter. In 2016 IEEE\/RSJ international conference on intelligent robots and systems (IROS) (pp. 598\u2013605). IEEE.","DOI":"10.1109\/IROS.2016.7759114"},{"issue":"2","key":"9969_CR8","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1002\/j.1538-7305.1950.tb00463.x","volume":"29","author":"RW Hamming","year":"1950","unstructured":"Hamming, R. W. (1950). Error detecting and error correcting codes. The Bell System Technical Journal, 29(2), 147\u2013160.","journal-title":"The Bell System Technical Journal"},{"key":"9969_CR9","doi-asserted-by":"crossref","unstructured":"Johns, E., Leutenegger, S., & Davison, A. J. (2016). Deep learning a grasp function for grasping under gripper pose uncertainty. In 2016 IEEE\/RSJ international conference on intelligent robots and systems (IROS) (pp. 4461\u20134468). IEEE.","DOI":"10.1109\/IROS.2016.7759657"},{"key":"9969_CR10","unstructured":"Kalashnikov, D., Irpan, A., Pastor, P. Ibarz, J., Herzog, A., Jang, E. Quillen, D., Holly, E., Kalakrishnan, M., & Vanhoucke V. et\u00a0al. (2018). Qt-opt: Scalable deep reinforcement learning for vision-based robotic manipulation. arXiv:1806.10293."},{"key":"9969_CR11","doi-asserted-by":"crossref","unstructured":"Kappler, D., Bohg, J., & Schaal, S. (2015) Leveraging big data for grasp planning. In 2015 IEEE international conference on robotics and automation (ICRA) (pp. 4304\u20134311). IEEE.","DOI":"10.1109\/ICRA.2015.7139793"},{"key":"9969_CR12","unstructured":"Kinga, D., & Adam, J. (2015). A method for stochastic optimization int. In Conference on learning representations (ICLR) ."},{"key":"9969_CR13","volume-title":"Chipmunk 2d physics engine","author":"S Lembcke","year":"2013","unstructured":"Lembcke, S. (2013). Chipmunk 2d physics engine. Inver Grove Heights: Howling Moon Software."},{"issue":"4\u20135","key":"9969_CR14","doi-asserted-by":"publisher","first-page":"705","DOI":"10.1177\/0278364914549607","volume":"34","author":"I Lenz","year":"2015","unstructured":"Lenz, I., Lee, H., & Saxena, A. (2015). Deep learning for detecting robotic grasps. The International Journal of Robotics Research, 34(4\u20135), 705\u2013724.","journal-title":"The International Journal of Robotics Research"},{"issue":"4\u20135","key":"9969_CR15","doi-asserted-by":"publisher","first-page":"421","DOI":"10.1177\/0278364917710318","volume":"37","author":"S Levine","year":"2018","unstructured":"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. The International Journal of Robotics Research, 37(4\u20135), 421\u2013436.","journal-title":"The International Journal of Robotics Research"},{"key":"9969_CR16","unstructured":"Mahler, J., & Goldberg, K. (2017). Learning deep policies for robot bin picking by simulating robust grasping sequences. In Conference on robot learning (pp. 515\u2013524)."},{"key":"9969_CR17","unstructured":"Mahler, J., Liang, J., Niyaz, S., Laskey, M., Doan, R., Liu, X., Ojea, J. A. & Goldberg, K. (2017). Dex-net 2.0: Deep learning to plan robust grasps with synthetic point clouds and analytic grasp metrics. arXiv:1703.09312."},{"issue":"1","key":"9969_CR18","doi-asserted-by":"publisher","first-page":"508","DOI":"10.1109\/LRA.2016.2519145","volume":"1","author":"J Mahler","year":"2016","unstructured":"Mahler, J., Pokorny, F. T., McCarthy, Z., van der Stappen, A. F., & Goldberg, K. (2016). Energy-bounded caging: Formal definition and 2-d energy lower bound algorithm based on weighted alpha shapes. IEEE Robotics and Automation Letters, 1(1), 508\u2013515.","journal-title":"IEEE Robotics and Automation Letters"},{"issue":"3","key":"9969_CR19","doi-asserted-by":"publisher","first-page":"908","DOI":"10.1109\/TASE.2018.2831724","volume":"15","author":"J Mahler","year":"2018","unstructured":"Mahler, J., Pokorny, F. T., Niyaz, S., & Goldberg, K. (2018). Synthesis of energy-bounded planar caging grasps using persistent homology. IEEE Transactions on Automation Science and Engineering, 15(3), 908\u2013918.","journal-title":"IEEE Transactions on Automation Science and Engineering"},{"key":"9969_CR20","doi-asserted-by":"crossref","unstructured":"Makapunyo, T., Phoka, T., Pipattanasomporn, P., Niparnan, N., & Sudsang, A. (2012) Measurement framework of partial cage quality. In 2012 IEEE international conference on robotics and biomimetics (ROBIO) (pp. 1812\u20131816). IEEE.","DOI":"10.1109\/ROBIO.2012.6491231"},{"key":"9969_CR21","doi-asserted-by":"crossref","unstructured":"Makita, S., & Maeda, Y. (2008). 3d multifingered caging: Basic formulation and planning. In 2008 IEEE\/RSJ international conference on intelligent robots and systems (pp. 2697\u20132702). IEEE.","DOI":"10.1109\/IROS.2008.4650895"},{"issue":"4","key":"9969_CR22","doi-asserted-by":"publisher","first-page":"263","DOI":"10.1504\/IJMA.2013.058376","volume":"3","author":"S Makita","year":"2013","unstructured":"Makita, S., Okita, K., & Maeda, Y. (2013). 3d two-fingered caging for two types of objects: Sufficient conditions and planning. International Journal of Mechatronics and Automation, 3(4), 263\u2013277.","journal-title":"International Journal of Mechatronics and Automation"},{"key":"9969_CR23","doi-asserted-by":"crossref","unstructured":"McCarthy, Z., Bretl, T., & Hutchinson, S. (2012). Proving path non-existence using sampling and alpha shapes. In 2012 IEEE international conference on robotics and automation (pp. 2563\u20132569). IEEE.","DOI":"10.1109\/ICRA.2012.6225300"},{"key":"9969_CR24","doi-asserted-by":"crossref","unstructured":"Pinto, L., & Gupta, A. (2016). Supersizing self-supervision: Learning to grasp from 50k tries and 700 robot hours. In IEEE international conference on robotics and automation (ICRA) (Vol. 2016, pp. 3406\u20133413). IEEE.","DOI":"10.1109\/ICRA.2016.7487517"},{"key":"9969_CR25","doi-asserted-by":"crossref","unstructured":"Pipattanasomporn, P., & Sudsang, A. (2006). Two-finger caging of concave polygo. In Proceedings 2006 IEEE international conference on robotics and automation, 2006. ICRA 2006 (pp. 2137\u20132142). IEEE.","DOI":"10.1109\/ROBOT.2006.1642020"},{"key":"9969_CR26","doi-asserted-by":"crossref","unstructured":"Pokorny, F. T., Stork, J. A. & Kragic, D. (2013). Grasping objects with holes: A topological approach. In 2013 IEEE international conference on robotics and automation (pp. 1100\u20131107). IEEE.","DOI":"10.1109\/ICRA.2013.6630710"},{"issue":"3","key":"9969_CR27","doi-asserted-by":"publisher","first-page":"299","DOI":"10.1177\/02783649922066222","volume":"18","author":"E Rimon","year":"1999","unstructured":"Rimon, E., & Blake, A. (1999). Caging planar bodies by one-parameter two-fingered gripping systems. The International Journal of Robotics Research, 18(3), 299\u2013318.","journal-title":"The International Journal of Robotics Research"},{"issue":"7","key":"9969_CR28","doi-asserted-by":"publisher","first-page":"886","DOI":"10.1177\/0278364912442972","volume":"31","author":"A Rodriguez","year":"2012","unstructured":"Rodriguez, A., Mason, M. T., & Ferry, S. (2012). From caging to grasping. The International Journal of Robotics Research, 31(7), 886\u2013900.","journal-title":"The International Journal of Robotics Research"},{"issue":"2","key":"9969_CR29","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1177\/0278364907087172","volume":"27","author":"A Saxena","year":"2008","unstructured":"Saxena, A., Driemeyer, J., & Ng, A. Y. (2008). Robotic grasping of novel objects using vision. The International Journal of Robotics Research, 27(2), 157\u2013173.","journal-title":"The International Journal of Robotics Research"},{"key":"9969_CR30","doi-asserted-by":"crossref","unstructured":"Stork, J. A., Pokorny, F. T., & Kragic, D. (2013a). A topology-based object representation for clasping, latching and hooking. In 2013 13th IEEE-RAS international conference on humanoid robots (humanoids) (pp. 138\u2013145). IEEE.","DOI":"10.1109\/HUMANOIDS.2013.7029968"},{"key":"9969_CR31","doi-asserted-by":"crossref","unstructured":"Stork, J. A., Pokorny, F. T., & Kragic, D. (2013a). Integrated motion and clasp planning with virtual linking. In IROS, Tokyo, Japan.","DOI":"10.1109\/IROS.2013.6696782"},{"key":"9969_CR32","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., et\u00a0al. (2015). Going deeper with convolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 1\u20139).","DOI":"10.1109\/CVPR.2015.7298594"},{"issue":"11","key":"9969_CR33","doi-asserted-by":"publisher","first-page":"2153","DOI":"10.1109\/TPAMI.2015.2408351","volume":"37","author":"AA Taha","year":"2015","unstructured":"Taha, A. A., & Hanbury, A. (2015). An efficient algorithm for calculating the exact Hausdorff distance. IEEE Transactions on Pattern Analysis and Machine Intelligence, 37(11), 2153\u20132163.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"11\u201312","key":"9969_CR34","doi-asserted-by":"publisher","first-page":"1308","DOI":"10.1177\/0278364908098485","volume":"27","author":"M Vahedi","year":"2008","unstructured":"Vahedi, M., & van der Stappen, A. F. (2008). Caging polygons with two and three fingers. The International Journal of Robotics Research, 27(11\u201312), 1308\u20131324.","journal-title":"The International Journal of Robotics Research"},{"key":"9969_CR35","unstructured":"Varava, A., Carvalho, J. F., Pokorny, F. T., & Kragic, D. (2018) Free space of rigid objects: Caging, path non-existence, and narrow passage detection. In Workshop on algorithmic foundations of robotics."},{"key":"9969_CR36","doi-asserted-by":"crossref","unstructured":"Varava, A., Welle, M. C., Mahler, J., Goldberg, K., Kragic, D. & Pokomy, F. T. (2019) Partial caging: A clearance-based definition and deep learning. In 2019 IEEE\/RSJ international conference on intelligent robots and systems (IROS) (pp. 1533\u20131540). IEEE.","DOI":"10.1109\/IROS40897.2019.8967958"},{"issue":"6","key":"9969_CR37","doi-asserted-by":"publisher","first-page":"1479","DOI":"10.1109\/TRO.2016.2602374","volume":"32","author":"A Varava","year":"2016","unstructured":"Varava, A., Kragic, D., & Pokorny, F. T. (2016). Caging grasps of rigid and partially deformable 3-d objects with double fork and neck features. IEEE Transactions Robotics, 32(6), 1479\u20131497.","journal-title":"IEEE Transactions Robotics"},{"issue":"1","key":"9969_CR38","doi-asserted-by":"publisher","first-page":"278","DOI":"10.1109\/TASE.2016.2620175","volume":"15","author":"W Wan","year":"2018","unstructured":"Wan, W., & Fukui, R. (2018). Efficient planar caging test using space mapping. IEEE Transactions on Automation Science and Engineering, 15(1), 278\u2013289.","journal-title":"IEEE Transactions on Automation Science and Engineering"},{"key":"9969_CR39","unstructured":"Zeng, A., Song, S., Yu, K.-T., Donlon, E., Hogan, F. R., Bauza, M., Ma, D., Taylor, O., Liu, M., & Romo, E. et\u00a0al. (2017). Robotic pick-and-place of novel objects in clutter with multi-affordance grasping and cross-domain image matching. arXiv:1710.01330."},{"issue":"11\u201312","key":"9969_CR40","doi-asserted-by":"publisher","first-page":"1246","DOI":"10.1177\/0278364908099216","volume":"27","author":"L Zhang","year":"2008","unstructured":"Zhang, L., Kim, Y. J., & Manocha, D. (2008). Efficient cell labelling and path non-existence computation using c-obstacle query. The International Journal of Robotics Research, 27(11\u201312), 1246\u20131257.","journal-title":"The International Journal of Robotics Research"}],"container-title":["Autonomous Robots"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10514-021-09969-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10514-021-09969-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10514-021-09969-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,14]],"date-time":"2022-12-14T19:32:44Z","timestamp":1671046364000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10514-021-09969-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,2,4]]},"references-count":40,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2021,6]]}},"alternative-id":["9969"],"URL":"https:\/\/doi.org\/10.1007\/s10514-021-09969-6","relation":{},"ISSN":["0929-5593","1573-7527"],"issn-type":[{"type":"print","value":"0929-5593"},{"type":"electronic","value":"1573-7527"}],"subject":[],"published":{"date-parts":[[2021,2,4]]},"assertion":[{"value":"26 February 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 January 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 February 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}