{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T05:26:16Z","timestamp":1773638776105,"version":"3.50.1"},"reference-count":32,"publisher":"Association for Computing Machinery (ACM)","issue":"6","license":[{"start":{"date-parts":[[2020,11,27]],"date-time":"2020-11-27T00:00:00Z","timestamp":1606435200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"GD Science and Technology Program","award":["2015A030312015"],"award-info":[{"award-number":["2015A030312015"]}]},{"name":"GD Higher Education Key Program","award":["2018KZDXM058"],"award-info":[{"award-number":["2018KZDXM058"]}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"crossref","award":["61872250, 61861130365, 61761146002"],"award-info":[{"award-number":["61872250, 61861130365, 61761146002"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Graph."],"published-print":{"date-parts":[[2020,12,31]]},"abstract":"<jats:p>\n            We introduce the\n            <jats:italic>transport-and-pack<\/jats:italic>\n            (TAP) problem, a frequently encountered instance of real-world packing, and develop a\n            <jats:italic>neural optimization<\/jats:italic>\n            solution based on\n            <jats:italic>reinforcement learning.<\/jats:italic>\n            Given an initial spatial configuration of boxes, we seek an efficient method to iteratively transport and pack the boxes compactly into a target container. Due to obstruction and accessibility constraints, our problem has to add a new search dimension, i.e., finding an optimal\n            <jats:italic>transport sequence<\/jats:italic>\n            , to the already immense search space for packing alone. Using a learning-based approach, a trained network can learn and encode solution patterns to guide the solution of new problem instances instead of executing an expensive online search. In our work, we represent the transport constraints using a\n            <jats:italic>precedence graph<\/jats:italic>\n            and train a neural network, coined TAP-Net, using reinforcement learning to reward\n            <jats:italic>efficient<\/jats:italic>\n            and\n            <jats:italic>stable<\/jats:italic>\n            packing. The network is built on an encoder-decoder architecture, where the encoder employs convolution layers to encode the box geometry and precedence graph and the decoder is a recurrent neural network (RNN) which inputs the current encoder output, as well as the current box packing state of the target container, and outputs the next box to pack, as well as its orientation. We train our network on\n            <jats:italic>randomly generated<\/jats:italic>\n            initial box configurations,\n            <jats:italic>without supervision<\/jats:italic>\n            , via policy gradients to learn optimal TAP policies to maximize packing efficiency and stability. We demonstrate the performance of TAP-Net on a variety of examples, evaluating the network through ablation studies and comparisons to baselines and alternative network designs. We also show that our network generalizes well to larger problem instances, when trained on small-sized inputs.\n          <\/jats:p>","DOI":"10.1145\/3414685.3417796","type":"journal-article","created":{"date-parts":[[2020,11,27]],"date-time":"2020-11-27T21:51:05Z","timestamp":1606513865000},"page":"1-15","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":38,"title":["TAP-Net"],"prefix":"10.1145","volume":"39","author":[{"given":"Ruizhen","family":"Hu","sequence":"first","affiliation":[{"name":"Shenzhen University"}]},{"given":"Juzhan","family":"Xu","sequence":"additional","affiliation":[{"name":"Shenzhen University"}]},{"given":"Bin","family":"Chen","sequence":"additional","affiliation":[{"name":"Shenzhen University"}]},{"given":"Minglun","family":"Gong","sequence":"additional","affiliation":[{"name":"University of Guelph"}]},{"given":"Hao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Simon Fraser University"}]},{"given":"Hui","family":"Huang","sequence":"additional","affiliation":[{"name":"Shenzhen University"}]}],"member":"320","published-online":{"date-parts":[[2020,11,27]]},"reference":[{"key":"e_1_2_2_1_1","unstructured":"Irwan Bello Hieu Pham Quoc V. Le Mohammad Norouzi and Samy Bengio. 2017. Neural Combinatorial Optimization with Reinforcement Learning. (2017). https:\/\/openreview.net\/forum?id=Bk9mxlSFx  Irwan Bello Hieu Pham Quoc V. Le Mohammad Norouzi and Samy Bengio. 2017. Neural Combinatorial Optimization with Reinforcement Learning. (2017). https:\/\/openreview.net\/forum?id=Bk9mxlSFx"},{"key":"e_1_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/508357.508360"},{"key":"e_1_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF02187720"},{"key":"e_1_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818087"},{"key":"e_1_2_2_5_1","volume-title":"Quantifying Generalization in Reinforcement Learning. CoRR abs\/1812.02341","author":"Cobbe Karl","year":"2018","unstructured":"Karl Cobbe , Oleg Klimov , Christopher Hesse , Taehoon Kim , and John Schulman . 2018. Quantifying Generalization in Reinforcement Learning. CoRR abs\/1812.02341 ( 2018 ). arXiv:1812.02341 http:\/\/arxiv.org\/abs\/1812.02341 Karl Cobbe, Oleg Klimov, Christopher Hesse, Taehoon Kim, and John Schulman. 2018. Quantifying Generalization in Reinforcement Learning. CoRR abs\/1812.02341 (2018). arXiv:1812.02341 http:\/\/arxiv.org\/abs\/1812.02341"},{"key":"e_1_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-019-0129-0"},{"key":"e_1_2_2_7_1","unstructured":"Lu Duan Haoyuan Hu Yu Qian Yu Gong Xiaodong Zhang Jiangwen Wei and Yinghui Xu. 2019. A Multi-task Selected Learning Approach for Solving 3D Flexible Bin Packing Problem. (2019) 1386--1394.  Lu Duan Haoyuan Hu Yu Qian Yu Gong Xiaodong Zhang Jiangwen Wei and Yinghui Xu. 2019. A Multi-task Selected Learning Approach for Solving 3D Flexible Bin Packing Problem. (2019) 1386--1394."},{"key":"e_1_2_2_8_1","volume-title":"The vehicle routing problem: latest advances and new challenges","author":"Golden Bruce L","unstructured":"Bruce L Golden , Subramanian Raghavan , and Edward A Wasil . 2008. The vehicle routing problem: latest advances and new challenges . Vol. 43 . Springer Science & Business Media . Bruce L Golden, Subramanian Raghavan, and Edward A Wasil. 2008. The vehicle routing problem: latest advances and new challenges. Vol. 43. Springer Science & Business Media."},{"key":"e_1_2_2_9_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 ). 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_10_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 . 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_11_1","doi-asserted-by":"crossref","unstructured":"Korhan Karabulut and Mustafa Murat \u0130nceo\u011flu. 2004. A hybrid genetic algorithm for packing in 3D with deepest bottom left with fill method. (2004) 441--450.  Korhan Karabulut and Mustafa Murat \u0130nceo\u011flu. 2004. A hybrid genetic algorithm for packing in 3D with deepest bottom left with fill method. (2004) 441--450.","DOI":"10.1007\/978-3-540-30198-1_45"},{"key":"e_1_2_2_12_1","volume-title":"Reddy","author":"Keneshloo Yaser","year":"2019","unstructured":"Yaser Keneshloo , Tian Shi , Naren Ramakrishnan , and Chandan K . Reddy . 2019 . Deep Reinforcement Learning For Sequence to Sequence Models. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS ( 2019). Yaser Keneshloo, Tian Shi, Naren Ramakrishnan, and Chandan K. Reddy. 2019. Deep Reinforcement Learning For Sequence to Sequence Models. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2019)."},{"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. 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":"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. 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_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201328"},{"key":"e_1_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3333002"},{"key":"e_1_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.1400421"},{"key":"e_1_2_2_18_1","volume-title":"Computer Graphics Forum","author":"Ma Yuexin","unstructured":"Yuexin Ma , Zhonggui Chen , Wenchao Hu , and Wenping Wang . 2018. Packing irregular objects in 3D space via hybrid optimization . In Computer Graphics Forum , Vol. 37 . Wiley Online Library , 49--59. Yuexin Ma, Zhonggui Chen, Wenchao Hu, and Wenping Wang. 2018. Packing irregular objects in 3D space via hybrid optimization. In Computer Graphics Forum, Vol. 37. Wiley Online Library, 49--59."},{"key":"e_1_2_2_19_1","volume-title":"International conference on machine learning. 1928--1937","author":"Mnih Volodymyr","year":"2016","unstructured":"Volodymyr Mnih , Adria Puigdomenech Badia , Mehdi Mirza , Alex Graves , Timothy Lillicrap , Tim Harley , David Silver , and Koray Kavukcuoglu . 2016 . Asynchronous methods for deep reinforcement learning . In International conference on machine learning. 1928--1937 . Volodymyr Mnih, Adria Puigdomenech Badia, Mehdi Mirza, Alex Graves, Timothy Lillicrap, Tim Harley, David Silver, and Koray Kavukcuoglu. 2016. Asynchronous methods for deep reinforcement learning. In International conference on machine learning. 1928--1937."},{"key":"e_1_2_2_20_1","volume-title":"An Efficient Exhaustive Search Algorithm for the Escherization Problem. Algorithmica","author":"Nagata Yuichi","year":"2020","unstructured":"Yuichi Nagata and Shinji Imahori . 2020. An Efficient Exhaustive Search Algorithm for the Escherization Problem. Algorithmica ( 2020 ), 1--33. Yuichi Nagata and Shinji Imahori. 2020. An Efficient Exhaustive Search Algorithm for the Escherization Problem. Algorithmica (2020), 1--33."},{"key":"e_1_2_2_21_1","unstructured":"MohammadReza Nazari Afshin Oroojlooy Lawrence Snyder and Martin Takac. 2018. Reinforcement Learning for Solving the Vehicle Routing Problem. (2018) 9839--9849. http:\/\/papers.nips.cc\/paper\/8190-reinforcement-learning-for-solving-the-vehicle-routing-problem.pdf  MohammadReza Nazari Afshin Oroojlooy Lawrence Snyder and Martin Takac. 2018. Reinforcement Learning for Solving the Vehicle Routing Problem. (2018) 9839--9849. http:\/\/papers.nips.cc\/paper\/8190-reinforcement-learning-for-solving-the-vehicle-routing-problem.pdf"},{"key":"e_1_2_2_22_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 . 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_23_1","volume-title":"Assessing Generalization in Deep Reinforcement Learning. CoRR abs\/1810.12282","author":"Packer Charles","year":"2018","unstructured":"Charles Packer , Katelyn Gao , Jernej Kos , Philipp Kr\u00e4henb\u00fchl , Vladlen Koltun , and Dawn Song . 2018. Assessing Generalization in Deep Reinforcement Learning. CoRR abs\/1810.12282 ( 2018 ). arXiv:1810.12282 http:\/\/arxiv.org\/abs\/1810.12282 Charles Packer, Katelyn Gao, Jernej Kos, Philipp Kr\u00e4henb\u00fchl, Vladlen Koltun, and Dawn Song. 2018. Assessing Generalization in Deep Reinforcement Learning. CoRR abs\/1810.12282 (2018). arXiv:1810.12282 http:\/\/arxiv.org\/abs\/1810.12282"},{"key":"e_1_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.trb.2016.06.003"},{"key":"e_1_2_2_25_1","article-title":"Interactive By-example Design of Artistic Packing Layouts","volume":"31","author":"Reinert Bernhard","year":"2013","unstructured":"Bernhard Reinert , Tobias Ritschel , and Hans-Peter Seidel . 2013 . Interactive By-example Design of Artistic Packing Layouts . ACM Trans. on Graphics 31 , 6 (2013). Bernhard Reinert, Tobias Ritschel, and Hans-Peter Seidel. 2013. Interactive By-example Design of Artistic Packing Layouts. ACM Trans. on Graphics 31, 6 (2013).","journal-title":"ACM Trans. on Graphics"},{"key":"e_1_2_2_26_1","doi-asserted-by":"crossref","unstructured":"Daniel Saakes Thomas Cambazard Jun Mitani and Takeo Igarashi. 2013. PacCAM: Material capture and interactive 2D packing for efficient material usage on CNC cutting machines. In ACM UIST.  Daniel Saakes Thomas Cambazard Jun Mitani and Takeo Igarashi. 2013. PacCAM: Material capture and interactive 2D packing for efficient material usage on CNC cutting machines. In ACM UIST.","DOI":"10.1145\/2501988.2501990"},{"key":"e_1_2_2_27_1","unstructured":"Pedro V Sander Zo\u00eb J Wood Steven Gortler John Snyder and Hugues Hoppe. 2003. Multi-chart geometry images. (2003).  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_28_1","volume-title":"Sequence to sequence learning with neural networks. Advances in NIPS","author":"Sutskever I","year":"2014","unstructured":"I Sutskever , O Vinyals , and QV Le. 2014. Sequence to sequence learning with neural networks. Advances in NIPS ( 2014 ). I Sutskever, O Vinyals, and QV Le. 2014. Sequence to sequence learning with neural networks. Advances in NIPS (2014)."},{"key":"e_1_2_2_29_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. 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_30_1","unstructured":"Oriol Vinyals Meire Fortunato and Navdeep Jaitly. 2015. Pointer Networks. (2015) 2692--2700. http:\/\/papers.nips.cc\/paper\/5866-pointer-networks.pdf  Oriol Vinyals Meire Fortunato and Navdeep Jaitly. 2015. Pointer Networks. (2015) 2692--2700. http:\/\/papers.nips.cc\/paper\/5866-pointer-networks.pdf"},{"key":"e_1_2_2_31_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.  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_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00201"}],"container-title":["ACM Transactions on Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3414685.3417796","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3414685.3417796","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:03:14Z","timestamp":1750197794000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3414685.3417796"}},"subtitle":["transport-and-pack using reinforcement learning"],"short-title":[],"issued":{"date-parts":[[2020,11,27]]},"references-count":32,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2020,12,31]]}},"alternative-id":["10.1145\/3414685.3417796"],"URL":"https:\/\/doi.org\/10.1145\/3414685.3417796","relation":{},"ISSN":["0730-0301","1557-7368"],"issn-type":[{"value":"0730-0301","type":"print"},{"value":"1557-7368","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,11,27]]},"assertion":[{"value":"2020-11-27","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}