PackingGPT: 3D Packing Agent for Real Furniture in Last-Mile Delivery

• URL: http://arxiv.org/abs/2608.01427v1
• Date: Sun, 02 Aug 2026 18:16:58 GMT
• Title: PackingGPT: 3D Packing Agent for Real Furniture in Last-Mile Delivery
• Abstract summary: This paper addresses the physically stable placement under realistic conditions with heterogeneous boxes and occupied containers.<n>It provides a real-world benchmark dataset and baseline model for the Heterogeneous furniture-in-vehicle packing task.<n>We also propose a PackingGPT framework for packing as a sequential placement inspired by the Lego assembly process.
• Score: 4.35456329158128
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 3D bin packing rectangular items into standardised containers to maximise space utilisation under geometric shipping automation. Loading a furniture purchase into a personal vehicle is the same task, but under more complex conditions that standard container loading algorithms ignore. This paper addresses the physically stable placement under these realistic conditions with heterogeneous boxes (e.g. varying dimensions and weights) and occupied containers (e.g. groceries). This paper provides a real-world benchmark dataset and baseline model for the Heterogeneous furniture-in-vehicle packing task. The dataset uses real furniture company flat-pack packaging data covering a large number of catalogue products via family-level extrapolation with diversity length, widths, heights, and weights. We also propose a PackingGPT framework for packing as a sequential placement inspired by the Lego assembly process, where heterogeneous boxes of varying dimensions (bricks) are placed step-by-step into the irregular remaining cargo space (creations). Five baseline packing methods were tested on our dataset without considering the Centre-of- Mass (CoM) constraints. In sedan car simulations, 10-40% of placed boxes failed the stability check on average. When the LLP model was trained on packing sequences with CoM constraints enforced during placement, the failure rate dropped to 0.67% (SUV-500).

Related papers

• PhyScensis: Physics-Augmented LLM Agents for Complex Physical Scene Arrangement [89.35154754765502]
  PhyScensis is an agent-based framework powered by a physics engine to produce physically plausible scene configurations.<n>Our framework preserves strong controllability over fine-grained textual descriptions and numerical parameters.<n> Experimental results show that our method outperforms prior approaches in scene complexity, visual quality, and physical accuracy.
  arXiv  Detail & Related papers  (2026-02-16T17:55:25Z)
• Pack it in: Packing into Partially Filled Containers Through Contact [0.8299692647308321]
  This paper presents a contact-aware packing approach that exploits purposeful interactions with previously placed objects to create free space.<n>It is achieved by using a multi-object trajectory controller integrated with a predictive model.<n>A method that suggests physically-feasible locations to place the object inside the container is presented.
  arXiv  Detail & Related papers  (2026-02-12T15:47:04Z)
• OPA-Pack: Object-Property-Aware Robotic Bin Packing [99.93418592774326]
  This paper presents OPA-Pack, the first framework that equips the robot with object property considerations in planning the object packing.<n>Also, we formulate OPA-Net, aiming to jointly separate incompatible object pairs and reduce pressure on fragile objects, while compacting the packing.<n> Experimental results manifest that OPA-Pack greatly improves the accuracy of separating incompatible object pairs and largely reduces pressure on fragile objects.
  arXiv  Detail & Related papers  (2025-05-19T16:48:14Z)
• Deliberate Planning of 3D Bin Packing on Packing Configuration Trees [65.05353662124676]
  Online 3D Bin Packing Problem (3D-BPP) has widespread applications in industrial automation.<n>We propose to enhance the practical applicability of online 3D-BPP via learning on a novel hierarchical representation, packing configuration tree (PCT)<n>PCT is a full-fledged description of the state and action space of bin packing which can support packing policy learning based on deep reinforcement learning (DRL)
  arXiv  Detail & Related papers  (2025-04-06T09:07:10Z)
• Convolutional Occupancy Models for Dense Packing of Complex, Novel Objects [75.54599721349037]
  We present a fully-convolutional shape completion model, F-CON, that can be easily combined with off-the-shelf planning methods for dense packing in the real world. We also release a simulated dataset, COB-3D-v2, that can be used to train shape completion models for real-word robotics applications. Finally, we equip a real-world pick-and-place system with F-CON, and demonstrate dense packing of complex, unseen objects in cluttered scenes.
  arXiv  Detail & Related papers  (2023-07-31T19:08:16Z)
• Benchmark dataset and instance generator for Real-World Three-Dimensional Bin Packing Problems [1.035593890158457]
  The benchmark was initially proposed to evaluate the performance of quantum solvers. The characteristics of this set of instances were designed according to the current limitations of quantum devices. The data introduced in this article provides a baseline that will encourage quantum computing researchers to work on real-world bin packing problems.
  arXiv  Detail & Related papers  (2023-04-28T09:29:43Z)
• Parcel3D: Shape Reconstruction from Single RGB Images for Applications in Transportation Logistics [62.997667081978825]
  We focus on enabling damage and tampering detection in logistics and tackle the problem of 3D shape reconstruction of potentially damaged parcels. We present a novel synthetic dataset, named Parcel3D, that is based on the Google Scanned Objects (GSO) dataset. We present a novel architecture called CubeRefine R-CNN, which combines estimating a 3D bounding box with an iterative mesh refinement.
  arXiv  Detail & Related papers  (2023-04-18T13:55:51Z)
• Hybrid Approach for Solving Real-World Bin Packing Problem Instances Using Quantum Annealers [0.8434687648198277]
  We introduce a hybrid quantum-classical framework for solving real-world three-dimensional Bin Packing Problems (Q4RealBPP) Q4RealBPP permits the solving of real-world oriented instances of 3dBPP, contemplating restrictions well appreciated by industrial and logistics sectors.
  arXiv  Detail & Related papers  (2023-03-01T14:04:50Z)
• Learning Physically Realizable Skills for Online Packing of General 3D Shapes [41.27652080050046]
  We study the problem of learning online packing skills for irregular 3D shapes. The goal is to consecutively move a sequence of 3D objects with arbitrary shapes into a designated container. We take physical realizability into account, involving physics dynamics and constraints of a placement.
  arXiv  Detail & Related papers  (2022-12-05T08:23:39Z)
• Planning Irregular Object Packing via Hierarchical Reinforcement Learning [85.64313062912491]
  We propose a deep hierarchical reinforcement learning approach to plan packing sequence and placement for irregular objects. We show that our approach can pack more objects with less time cost than the state-of-the-art packing methods of irregular objects.
  arXiv  Detail & Related papers  (2022-11-17T07:16:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.