paper-with-me

홈 › Papers

OPA-Pack: Object-Property-Aware Robotic Bin Packing

2025-05-19 · Jia-Hui Pan, Yeok Tatt Cheah, Zhengzhe Liu, Ka-Hei Hui, Xiaojie Gao, Pheng-Ann Heng, Yun-hui Liu, Chi-Wing Fu

Robotic bin packing aids in a wide range of real-world scenarios such as e-commerce and warehouses. Yet, existing works focus mainly on considering the shape of objects to optimize packing compactness and neglect object properties such as fragility, edibility, and chemistry that humans typically consider when packing objects. This paper presents OPA-Pack (Object-Property-Aware Packing framework), the first framework that equips the robot with object property considerations in planning the object packing. Technical-wise, we develop a novel object property recognition scheme with retrieval-augmented generation and chain-of-thought reasoning, and build a dataset with object property annotations for 1,032 everyday objects. Also, we formulate OPA-Net, aiming to jointly separate incompatible object pairs and reduce pressure on fragile objects, while compacting the packing. Further, OPA-Net consists of a property embedding layer to encode the property of candidate objects to be packed, together with a fragility heightmap and an avoidance heightmap to keep track of the packed objects. Then, we design a reward function and adopt a deep Q-learning scheme to train OPA-Net. Experimental results manifest that OPA-Pack greatly improves the accuracy of separating incompatible object pairs (from 52% to 95%) and largely reduces pressure on fragile objects (by 29.4%), while maintaining good packing compactness. Besides, we demonstrate the effectiveness of OPA-Pack on a real packing platform, showcasing its practicality in real-world scenarios.

📄 PDF Abstract BibTeX arXiv:2505.13339

Code (0)

등록된 구현이 없습니다.

Tasks

ObjectQ-LearningRetrieval-augmented Generation

Methods 이 논문이 사용한 방법론

ADOPT Please enter a description about the method here
Focus 설명 없음
Q-Learning Q-Learning is an off-policy temporal difference control algorithm: $$Q\left(S\_{t}, A\_{t}\right) \leftarrow Q\left(S\_{t}, A\_{t}\right) + \alpha\left[R_{t+1} +…

Similar Papers 제목 키워드 기반

PackLab: A Comprehensive Framework for Developing, Training, and Evaluating MLLMs in Robotic Bin Packing

2026-09-20 · Donghao Zhou, Jia-Hui Pan, Fan Zhang, Xingyuan Bu 외 hf

Robotic bin packing requires long-horizon sequential decision-making, as each object placement affects the available space for subsequent packing. Existing methods primarily rely on hand-crafted geometric heuristics that…

Reinforcement Learning

Planning Irregular Object Packing via Hierarchical Reinforcement Learning

2022-11-17 · Sichao Huang, Ziwei Wang, Jie zhou, Jiwen Lu

Object packing by autonomous robots is an im-portant challenge in warehouses and logistics industry. Most conventional data-driven packing planning approaches focus on regular cuboid packing, which are usually heuristic …

Hierarchical Reinforcement LearningObjectQ-Learningreinforcement-learning+2

Robotic Manipulation Framework Based on Semantic Keypoints for Packing Shoes of Different Sizes, Shapes, and Softness

2025-09-07 · Yi Dong, Yangjun Liu, Jinjun Duan, Yang Li 외 arxiv

With the rapid development of the warehousing and logistics industries, the packing of goods has gradually attracted the attention of academia and industry. The packing of footwear products is a typical representative pa…

HERB: Human-augmented Efficient Reinforcement learning for Bin-packing

2025-04-23 · Gojko Perovic, Nuno Ferreira Duarte, Atabak Dehban, Gonçalo Teixeira 외 arxiv

Packing objects efficiently is a fundamental problem in logistics, warehouse automation, and robotics. When dealing with highly diverse 3D objects (household or grocery items), closed-form solutions are infeasible, and h…

Reinforcement Learning

Low-Resolution Perception for Robotic Packing

2026-08-26 · Giuseppe Fabio Preziosa, Federico Vignoni, Chiara Castellano, Marco Faroni 외 arxiv

This work tackles the problem of scalable perception for robotic packing with low-cost, low-resolution depth sensing. We propose a framework where reconstruction cues drive next-view selection and grasp evidence updates …