Abstract
We tackle the online 3D bin packing problem (3D-BPP), a challenging yet practically useful variant of the classical bin packing problem. In this problem, the items are delivered to the agent without informing the full sequence information. The agent must directly pack these items into the target bin stably without changing their arrival order, and no further adjustment is permitted. Online 3D-BPP can be naturally formulated as a Markov decision process (MDP). We adopt deep reinforcement learning, in particular, the on-policy actor-critic framework, to solve this MDP with constrained action space. To learn a practically feasible packing policy, we propose three critical designs. First, we propose an online analysis of packing stability based on a novel stacking tree. It attains a high analysis accuracy while reducing the computational complexity from O(N2) to O(N log N), making it especially suited for reinforcement learning training. Second, we propose a decoupled packing policy learning for different dimensions of placement which enables high-resolution spatial discretization and hence high packing precision. Third, we introduce a reward function that dictates the robot to place items in a far-to-near order and therefore simplifies the collision avoidance in movement planning of the robotic arm. Furthermore, we provide a comprehensive discussion on several key implemental issues. The extensive evaluation demonstrates that our learned policy outperforms the state-of-the-art methods significantly and is practically usable for real-world applications.
Similar content being viewed by others
References
Korte B, Vygen J. Bin-packing. In: Kombinatorische Optimierung. Berlin: Springer, 2012. 499–516
Martello S, Pisinger D, Vigo D. The three-dimensional bin packing problem. Oper Res, 2000, 48: 256–267
Crainic T G, Perboli G, Tadei R. Extreme point-based heuristics for three-dimensional bin packing. Informs J Comput, 2008, 20: 368–384
Karabulut K, İnceoğlu M M. A hybrid genetic algorithm for packing in 3D with deepest bottom left with fill method. In: Proceedings of International Conference on Advances in Information Systems, 2004. 441–450
Zhao H, She Q, Zhu C, et al. Online 3D bin packing with constrained deep reinforcement learning. In: Proceedings of the 35th AAAI Conference on Artificial Intelligence, the 33rd Conference on Innovative Applications of Artificial Intelligence, the 11th Symposium on Educational Advances in Artificial Intelligence, 2021. 741–749
Altman E. Constrained Markov Decision Processes. Boca Raton: CRC Press, 1999
Mnih V, Badia A P, Mirza M, et al. Asynchronous methods for deep reinforcement learning. In: Proceedings of International Conference on Machine Learning, 2016. 1928–1937
Wu Y, Mansimov E, Grosse R B, et al. Scalable trust-region method for deep reinforcement learning using kronecker-factored approximation. In: Proceedings of Advances in Neural Information Processing Systems, 2017. 5279–5288
Kantorovich L V. Mathematical methods of organizing and planning production. Manage Sci, 1960, 6: 366–422
Coffman E G, Garey M R, Johnson D S. Approximation algorithms for bin-packing—an updated survey. In: Proceedings of Algorithm Design for Computer System Design, 1984. 49–106
Faroe O, Pisinger D, Zachariasen M. Guided local search for the three-dimensional bin-packing problem. Informs J Comput, 2003, 15: 267–283
de Castro S J L, Soma N Y, Maculan N. A greedy search for the three-dimensional bin packing problem: the packing static stability case. Int Trans Oper Res, 2003, 10: 141–153
Lodi A, Martello S, Vigo D. Approximation algorithms for the oriented two-dimensional bin packing problem. Eur J Oper Res, 1999, 112: 158–166
Crainic T G, Perboli G, Tadei R. TS2PACK: a two-level tabu search for the three-dimensional bin packing problem. Eur J Oper Res, 2009, 195: 744–760
Li X, Zhao Z, Zhang K. A genetic algorithm for the three-dimensional bin packing problem with heterogeneous bins. In: Proceedings of Industrial and Systems Engineering Research Conference, 2014. 2039
Takahara S, Miyamoto S. An evolutionary approach for the multiple container loading problem. In: Proceedings of the 5th International Conference on Hybrid Intelligent Systems, 2005. 227–232
Ha C T, Nguyen T T, Bui L T, et al. An online packing heuristic for the three-dimensional container loading problem in dynamic environments and the physical internet. In: Proceedings of European Conference on the Applications of Evolutionary Computation, 2017. 140–155
Wang R, Nguyen T T, Kavakeb S, et al. Benchmarking dynamic three-dimensional bin packing problems using discrete-event simulation. In: Proceedings of European Conference on the Applications of Evolutionary Computation, 2016. 266–279
Hong Y D, Kim Y J, Lee K B. Smart pack: online autonomous object-packing system using RGB-D sensor data. Sensors, 2020, 20: 4448
Erleben K. Velocity-based shock propagation for multibody dynamics animation. ACM Trans Graph, 2007, 26: 12
Thomsen K K, Kraus M. Simulating small-scale object stacking using stack stability. In: Proceedings of the 23rd International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision WSCG 2015. Plzen: Vaclav Skala-UNION Agency, 2015. 5–8
Hsu S W, Keyser J. Automated constraint placement to maintain pile shape. ACM Trans Graph, 2012, 31: 1–6
Han D, Hsu S W, McNamara A, et al. Believability in simplifications of large scale physically based simulation. In: Proceedings of the ACM Symposium on Applied Perception, 2013. 99–106
Lillicrap T P, Hunt J J, Pritzel A, et al. Continuous control with deep reinforcement learning. 2015. ArXiv:1509.02971
Mnih V, Kavukcuoglu K, Silver D, et al. Human-level control through deep reinforcement learning. Nature, 2015, 518: 529–533
Wang Z, Schaul T, Hessel M, et al. Dueling network architectures for deep reinforcement learning. 2015. ArXiv:1511.06581
Silver D, Lever G, Heess N, et al. Deterministic policy gradient algorithms. In: Proceedings of the 31st International Conference on International Conference on Machine Learning, 2014. 387–395
Barth-Maron G, Hoffman M W, Budden D, et al. Distributed distributional deterministic policy gradients. 2018. ArXiv:1804.08617
Schulman J, Wolski F, Dhariwal P, et al. Proximal policy optimization algorithms. 2017. ArXiv:1707.06347
Bello I, Pham H, Le Q V, et al. Neural combinatorial optimization with reinforcement learning. 2016. ArXiv:1611.09940
Kool W, van Hoof H, Welling M. Attention, learn to solve routing problems! In: Proceedings of the 7th International Conference on Learning Representations, 2019
Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need. In: Proceedings of Annual Conference on Neural Information Processing Systems, Long Beach, 2017. 5998–6008
Zhang C, Song W, Cao Z, et al. Learning to dispatch for job shop scheduling via deep reinforcement learning. In: Proceedings of Annual Conference on Neural Information Processing Systems, 2020
Wang H, Liang W, Yu L F. Scene mover: automatic move planning for scene arrangement by deep reinforcement learning. ACM Trans Graph, 2020, 39: 1–15
Hu H, Zhang X, Yan X, et al. Solving a new 3D bin packing problem with deep reinforcement learning method. 2017. ArXiv:1708.05930
Laterre A, Fu Y, Jabri M K, et al. Ranked reward: enabling self-play reinforcement learning for combinatorial optimization. 2018. ArXiv:1807.01672
Uchibe E, Doya K. Constrained reinforcement learning from intrinsic and extrinsic rewards. In: Proceedings of the 6th International Conference on Development and Learning, 2007. 163–168
Chow Y, Ghavamzadeh M, Janson L, et al. Risk-constrained reinforcement learning with percentile risk criteria. J Mach Learn Res, 2017, 18: 6070–6120
Achiam J, Held D, Tamar A, et al. Constrained policy optimization. In: Proceedings of the 34th International Conference on Machine Learning-Volume 70, 2017. 22–31
Martens J, Grosse R. Optimizing neural networks with Kronecker-factored approximate curvature. In: Proceedings of International Conference on Machine Learning, 2015. 2408–2417
Haarnoja T, Zhou A, Abbeel P, et al. Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. 2018. ArXiv:1801.01290
Martello S, Pisinger D, Vigo D, et al. Algorithm 864: general and robot-packable variants of the three-dimensional bin packing problem. ACM Trans Math Softw, 2007, 33: 7
Tavakoli A, Pardo F, Kormushev P. Action branching architectures for deep reinforcement learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, 2018
Silver D, Schrittwieser J, Simonyan K, et al. Mastering the game of Go without human knowledge. Nature, 2017, 550: 354–359
Chaslot G M B, Winands M H, van den Herik H J. Parallel Monte-Carlo tree search. In: Proceedings of International Conference on Computers and Games, 2008. 60–71
Dekel A, Harenstam-Nielsen L, Caccamo S. Optimal least-squares solution to the hand-eye calibration problem. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020. 13598–13606
Feng C, Taguchi Y, Kamat V R. Fast plane extraction in organized point clouds using agglomerative hierarchical clustering. In: Proceedings of IEEE International Conference on Robotics and Automation (ICRA), 2014. 6218–6225
Paszke A, Gross S, Massa F, et al. PyTorch: an imperative style, high-performance deep learning library. In: Proceedings of Advances in Neural Information Processing Systems, 2019. 8024–8035
Gilmore P C, Gomory R E. A linear programming approach to the cutting-stock problem. Oper Res, 1961, 9: 849–859
Coumans E. Bullet physics simulation. In: Proceedings of ACM SIGGRAPH 2015 Courses, 2015
Acknowledgements
This work was supported in part by National Key Research and Development Program of China (Grant No. 2018AAA0102200), National Natural Science Foundation of China (Grant Nos. 62132021, 61825305, 62002375, 62002376, 62102435), NUDT Research Grants (Grant No. ZK19-30), DEGP Key Project (Grant No. 2018KZDXM058), GD Science and Technology Program (Grant No. 2020A0505100064), and Shenzhen Science and Technology Program (Grant No. JCYJ20210324120213036). We thank Qijin SHE, Yin YANG, Kun HUANG, Yixing LAN, Kaiwen LI, Junkai REN, and Yao DUAN for active discussion. We also thank Hanchi HUANG for maintaining a good community to communicate reinforcement learning related technologies.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Zhao, H., Zhu, C., Xu, X. et al. Learning practically feasible policies for online 3D bin packing. Sci. China Inf. Sci. 65, 112105 (2022). https://doi.org/10.1007/s11432-021-3348-6
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s11432-021-3348-6