Preference-Conditioned Reinforcement Learning for Space-Time Efficient Online 3D Bin Packing
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910045971677184 |
|---|---|
| author | Sarawgi, Nikita Manyar, Omey M. Wang, Fan Nguyen, Thinh H. Seita, Daniel Gupta, Satyandra K. |
| author_facet | Sarawgi, Nikita Manyar, Omey M. Wang, Fan Nguyen, Thinh H. Seita, Daniel Gupta, Satyandra K. |
| contents | Robotic bin packing is widely deployed in warehouse automation, with current systems achieving robust performance through heuristic and learning-based strategies. These systems must balance compact placement with rapid execution, where selecting alternative items or reorienting them can improve space utilization but introduce additional time. We propose a selection-based formulation that explicitly reasons over this trade-off: at each step, the robot evaluates multiple candidate actions, weighing expected packing benefit against estimated operational time. This enables time-aware strategies that selectively accept increased operational time when it yields meaningful spatial improvements. Our method, STEP (Space-Time Efficient Packing), uses a preference-conditioned, Transformer-based reinforcement learning policy, and allows generalization across candidate set sizes and integration with standard placement modules. It achieves a 44% reduction in operational time without compromising packing density. Additional material is available at https://step-packing.github.io. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_07800 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Preference-Conditioned Reinforcement Learning for Space-Time Efficient Online 3D Bin Packing Sarawgi, Nikita Manyar, Omey M. Wang, Fan Nguyen, Thinh H. Seita, Daniel Gupta, Satyandra K. Robotics Robotic bin packing is widely deployed in warehouse automation, with current systems achieving robust performance through heuristic and learning-based strategies. These systems must balance compact placement with rapid execution, where selecting alternative items or reorienting them can improve space utilization but introduce additional time. We propose a selection-based formulation that explicitly reasons over this trade-off: at each step, the robot evaluates multiple candidate actions, weighing expected packing benefit against estimated operational time. This enables time-aware strategies that selectively accept increased operational time when it yields meaningful spatial improvements. Our method, STEP (Space-Time Efficient Packing), uses a preference-conditioned, Transformer-based reinforcement learning policy, and allows generalization across candidate set sizes and integration with standard placement modules. It achieves a 44% reduction in operational time without compromising packing density. Additional material is available at https://step-packing.github.io. |
| title | Preference-Conditioned Reinforcement Learning for Space-Time Efficient Online 3D Bin Packing |
| topic | Robotics |
| url | https://arxiv.org/abs/2603.07800 |