arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.09694cs.RO
收藏

一种结合物体重排与稳定放置的高效在线三维装箱深度强化学习模型

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

School of Information Science, Japan Advanced Institute of Science and Technology(日本先进科学技术学院信息科学学院)

Peiwen Zhou, Ziyan Gao, Chenghao Li, Nak Young Chong

AI总结:

针对在线三维装箱这一NP难问题,本文提出融合物理启发式算法、物体重排与稳定放置的深度强化学习框架,可在更少训练轮次下提升空间利用率、减少浪费。

摘要:

本文提出了一种用于在线三维装箱(3D-BPP)的高效深度强化学习(DRL)框架。3D-BPP是一类NP难问题,在物流、仓储与运输领域具有重要意义,其核心是在箱子内部实现物体的最优排布。传统启发式算法往往无法应对实时场景中的动态约束与物理约束。我们提出了一种全新的DRL框架,该框架融合了可靠的物理启发式算法,同时具备物体重排与稳定放置机制。实验结果表明,所提框架实现了更高的空间利用率,能以更少的训练轮次有效减少空间浪费。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑