Preference-Conditioned Reinforcement Learning for Space-Time Efficient Online 3D Bin Packing

TL;DR

This paper introduces STEP, a preference-conditioned reinforcement learning approach for online 3D bin packing that balances space utilization and operational time, significantly reducing packing time while maintaining density.

Contribution

We propose a novel Transformer-based RL method that explicitly reasons over space-time trade-offs, enabling more efficient and adaptable robotic bin packing.

Findings

44% reduction in operational time

Maintains packing density comparable to existing methods

Generalizes across candidate set sizes

Abstract

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.