An Efficient Deep Reinforcement Learning Model for Online 3D Bin Packing Combining Object Rearrangement and Stable Placement

TL;DR

This paper introduces a deep reinforcement learning framework for online 3D bin packing that effectively combines physics heuristics and object rearrangement to improve space utilization in real-time applications.

Contribution

The paper proposes a novel DRL framework integrating physics heuristics and object rearrangement for efficient online 3D bin packing, addressing real-time constraints.

Findings

Achieves higher space utilization rates.

Reduces wasted space effectively.

Requires fewer training epochs.

Abstract

This paper presents an efficient deep reinforcement learning (DRL) framework for online 3D bin packing (3D-BPP). The 3D-BPP is an NP-hard problem significant in logistics, warehousing, and transportation, involving the optimal arrangement of objects inside a bin. Traditional heuristic algorithms often fail to address dynamic and physical constraints in real-time scenarios. We introduce a novel DRL framework that integrates a reliable physics heuristic algorithm and object rearrangement and stable placement. Our experiment show that the proposed framework achieves higher space utilization rates effectively minimizing the amount of wasted space with fewer training epochs.