NeSyPack: A Neuro-Symbolic Framework for Bimanual Logistics Packing

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Bowei, Yu, Peiqi, Tang, Zhenran, Zhou, Han, Sun, Yifan, Liu, Ruixuan, Liu, Changliu
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916782806138880
author Li, Bowei
Yu, Peiqi
Tang, Zhenran
Zhou, Han
Sun, Yifan
Liu, Ruixuan
Liu, Changliu
author_facet Li, Bowei
Yu, Peiqi
Tang, Zhenran
Zhou, Han
Sun, Yifan
Liu, Ruixuan
Liu, Changliu
contents This paper presents NeSyPack, a neuro-symbolic framework for bimanual logistics packing. NeSyPack combines data-driven models and symbolic reasoning to build an explainable hierarchical system that is generalizable, data-efficient, and reliable. It decomposes a task into subtasks via hierarchical reasoning, and further into atomic skills managed by a symbolic skill graph. The graph selects skill parameters, robot configurations, and task-specific control strategies for execution. This modular design enables robustness, adaptability, and efficient reuse - outperforming end-to-end models that require large-scale retraining. Using NeSyPack, our team won the First Prize in the What Bimanuals Can Do (WBCD) competition at the 2025 IEEE International Conference on Robotics and Automation.
format Preprint
id arxiv_https___arxiv_org_abs_2506_06567
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle NeSyPack: A Neuro-Symbolic Framework for Bimanual Logistics Packing
Li, Bowei
Yu, Peiqi
Tang, Zhenran
Zhou, Han
Sun, Yifan
Liu, Ruixuan
Liu, Changliu
Robotics
This paper presents NeSyPack, a neuro-symbolic framework for bimanual logistics packing. NeSyPack combines data-driven models and symbolic reasoning to build an explainable hierarchical system that is generalizable, data-efficient, and reliable. It decomposes a task into subtasks via hierarchical reasoning, and further into atomic skills managed by a symbolic skill graph. The graph selects skill parameters, robot configurations, and task-specific control strategies for execution. This modular design enables robustness, adaptability, and efficient reuse - outperforming end-to-end models that require large-scale retraining. Using NeSyPack, our team won the First Prize in the What Bimanuals Can Do (WBCD) competition at the 2025 IEEE International Conference on Robotics and Automation.
title NeSyPack: A Neuro-Symbolic Framework for Bimanual Logistics Packing
topic Robotics
url https://arxiv.org/abs/2506.06567