{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T18:06:50Z","timestamp":1787162810666,"version":"build-2736575974"},"reference-count":28,"publisher":"Association for Computing Machinery (ACM)","issue":"6","license":[{"start":{"date-parts":[[2023,12,5]],"date-time":"2023-12-05T00:00:00Z","timestamp":1701734400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100003453","name":"Guangdong Natural Science Foundation","doi-asserted-by":"crossref","award":["2021B1515020085"],"award-info":[{"award-number":["2021B1515020085"]}],"id":[{"id":"10.13039\/501100003453","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"crossref","award":["62322207, U2001206, 62161146005, U21B2023"],"award-info":[{"award-number":["62322207, U2001206, 62161146005, U21B2023"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Shenzhen Science and Technology Program","award":["RCYX20210609103121030"],"award-info":[{"award-number":["RCYX20210609103121030"]}]},{"name":"DEGP Innovation Team","award":["2022KCXTD025"],"award-info":[{"award-number":["2022KCXTD025"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Graph."],"published-print":{"date-parts":[[2023,12,5]]},"abstract":"<jats:p>\n                    We present a novel learning framework to solve the transport-and-packing (TAP) problem in 3D. It constitutes a full solution pipeline from partial observations of input objects via RGBD sensing and recognition to final box placement, via robotic motion planning, to arrive at a compact packing in a target container. The technical core of our method is a neural network for TAP, trained via\n                    <jats:italic toggle=\"yes\">reinforcement learning<\/jats:italic>\n                    (RL), to solve the NP-hard combinatorial optimization problem. Our network simultaneously selects an object to pack and determines the final packing location, based on a judicious encoding of the continuously evolving states of partially observed source objects and available spaces in the target container, using separate encoders both enabled with attention mechanisms. The encoded feature vectors are employed to compute the matching scores and feasibility masks of different pairings of box selection and available space configuration for packing strategy optimization. Extensive experiments, including ablation studies and physical packing execution by a real robot (Universal Robot UR5e), are conducted to evaluate our method in terms of its design choices, scalability, generalizability, and comparisons to baselines, including the most recent RL-based TAP solution. We also contribute the first benchmark for TAP which covers a variety of input settings and difficulty levels.\n                  <\/jats:p>","DOI":"10.1145\/3618354","type":"journal-article","created":{"date-parts":[[2023,12,5]],"date-time":"2023-12-05T10:20:48Z","timestamp":1701771648000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["Neural Packing: from Visual Sensing to Reinforcement Learning"],"prefix":"10.1145","volume":"42","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5132-238X","authenticated-orcid":false,"given":"Juzhan","family":"Xu","sequence":"first","affiliation":[{"name":"Shenzhen University, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5820-5381","authenticated-orcid":false,"given":"Minglun","family":"Gong","sequence":"additional","affiliation":[{"name":"University of Guelph, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1991-119X","authenticated-orcid":false,"given":"Hao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Simon Fraser University, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3212-0544","authenticated-orcid":false,"given":"Hui","family":"Huang","sequence":"additional","affiliation":[{"name":"Shenzhen University, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6798-0336","authenticated-orcid":false,"given":"Ruizhen","family":"Hu","sequence":"additional","affiliation":[{"name":"Shenzhen University, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,12,5]]},"reference":[{"key":"e_1_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.tre.2012.06.005"},{"key":"e_1_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818087"},{"key":"e_1_2_2_3_1","unstructured":"Erwin Coumans and Yunfei Bai. 2016. Pybullet a python module for physics simulation for games robotics and machine learning. (2016)."},{"key":"e_1_2_2_4_1","volume-title":"Extreme point-based heuristics for three-dimensional bin packing. Informs Journal on computing 20, 3","author":"Crainic Teodor Gabriel","year":"2008","unstructured":"Teodor Gabriel Crainic, Guido Perboli, and Roberto Tadei. 2008. Extreme point-based heuristics for three-dimensional bin packing. Informs Journal on computing 20, 3 (2008), 368--384."},{"key":"e_1_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-019-0129-0"},{"key":"e_1_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-55792-2_10"},{"key":"e_1_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"e_1_2_2_8_1","volume-title":"Solving a new 3d bin packing problem with deep reinforcement learning method. arXiv preprint arXiv:1708.05930","author":"Hu Haoyuan","year":"2017","unstructured":"Haoyuan Hu, Xiaodong Zhang, Xiaowei Yan, Longfei Wang, and Yinghui Xu. 2017. Solving a new 3d bin packing problem with deep reinforcement learning method. arXiv preprint arXiv:1708.05930 (2017)."},{"key":"e_1_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417764"},{"key":"e_1_2_2_10_1","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition. 2171--2178","author":"Jiang Hao","year":"2013","unstructured":"Hao Jiang and Jianxiong Xiao. 2013. A linear approach to matching cuboids in RGBDimages. In Proceedings of the IEEE conference on computer vision and pattern recognition. 2171--2178."},{"key":"e_1_2_2_11_1","volume-title":"Escherization. In Proceedings of the 27th annual conference on Computer graphics and interactive techniques. 499--510","author":"Kaplan Craig S","year":"2000","unstructured":"Craig S Kaplan and David H Salesin. 2000. Escherization. In Proceedings of the 27th annual conference on Computer graphics and interactive techniques. 499--510."},{"key":"e_1_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30198-1_45"},{"key":"e_1_2_2_13_1","volume-title":"Towards zero-waste furniture design","author":"Koo Bongjin","year":"2016","unstructured":"Bongjin Koo, Jean Hergel, Sylvain Lefebvre, and Niloy J Mitra. 2016. Towards zero-waste furniture design. IEEE transactions on visualization and computer graphics 23, 12 (2016), 2627--2640."},{"key":"e_1_2_2_14_1","volume-title":"Alain-Sam Cohen, David Kas, Karl Hajjar, Torbjorn S Dahl, Amine Kerkeni, and Karim Beguir.","author":"Laterre Alexandre","year":"2018","unstructured":"Alexandre Laterre, Yunguan Fu, Mohamed Khalil Jabri, Alain-Sam Cohen, David Kas, Karl Hajjar, Torbjorn S Dahl, Amine Kerkeni, and Karim Beguir. 2018. Ranked reward: Enabling self-play reinforcement learning for combinatorial optimization. arXiv preprint arXiv:1807.01672 (2018)."},{"key":"e_1_2_2_15_1","volume-title":"ACM transactions on graphics (TOG)","author":"L\u00e9vy Bruno","unstructured":"Bruno L\u00e9vy, Sylvain Petitjean, Nicolas Ray, and J\u00e9rome Maillot. 2002. Least squares conformal maps for automatic texture atlas generation. In ACM transactions on graphics (TOG), Vol. 21. ACM, 362--371."},{"key":"e_1_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2015.10.007"},{"key":"e_1_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201328"},{"key":"e_1_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0377-2217(02)00134-0"},{"key":"e_1_2_2_19_1","volume-title":"The three-dimensional bin packing problem. Operations research 48, 2","author":"Martello Silvano","year":"2000","unstructured":"Silvano Martello, David Pisinger, and Daniele Vigo. 2000. The three-dimensional bin packing problem. Operations research 48, 2 (2000), 256--267."},{"key":"e_1_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/1206040.1206047"},{"key":"e_1_2_2_21_1","volume-title":"Proc. of Eurographics Conference on Rendering (EGSR). 1309--1317","author":"N\u00f6ll Tobias","year":"2011","unstructured":"Tobias N\u00f6ll and Didier Stricker. 2011. Efficient Packing of Arbitrarily Shaped Charts for Automatic Texture Atlas Generation. In Proc. of Eurographics Conference on Rendering (EGSR). 1309--1317."},{"key":"e_1_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1287\/ijoc.1070.0254"},{"key":"e_1_2_2_23_1","unstructured":"Pedro V Sander Zo\u00eb J Wood Steven Gortler John Snyder and Hugues Hoppe. 2003. Multi-chart geometry images. (2003)."},{"key":"e_1_2_2_24_1","volume-title":"Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347","author":"Schulman John","year":"2017","unstructured":"John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. 2017. Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)."},{"key":"e_1_2_2_25_1","volume-title":"Bedrich Benes, R M\u011bch, N Carr, Ondrej Stava, and GS Miller.","author":"Vanek Juraj","year":"2014","unstructured":"Juraj Vanek, JA Garcia Galicia, Bedrich Benes, R M\u011bch, N Carr, Ondrej Stava, and GS Miller. 2014. PackMerger: A 3D print volume optimizer. In Computer Graphics Forum, Vol. 33. Wiley Online Library, 322--332."},{"key":"e_1_2_2_26_1","doi-asserted-by":"crossref","unstructured":"Fan Wang and Kris Hauser. 2019. Stable bin packing of non-convex 3D objects with a robot manipulator. (2019) 8698--8704.","DOI":"10.1109\/ICRA.2019.8794049"},{"key":"e_1_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i1.16155"},{"key":"e_1_2_2_28_1","volume-title":"International Conference on Learning Representations.","author":"Zhao Hang","year":"2021","unstructured":"Hang Zhao, Yang Yu, and Kai Xu. 2021b. Learning Efficient Online 3D Bin Packing on Packing Configuration Trees. In International Conference on Learning Representations."}],"container-title":["ACM Transactions on Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3618354","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3618354","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T10:47:14Z","timestamp":1755773234000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3618354"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,5]]},"references-count":28,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2023,12,5]]}},"alternative-id":["10.1145\/3618354"],"URL":"https:\/\/doi.org\/10.1145\/3618354","relation":{},"ISSN":["0730-0301","1557-7368"],"issn-type":[{"value":"0730-0301","type":"print"},{"value":"1557-7368","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12,5]]},"assertion":[{"value":"2023-12-05","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}