Saved in:
Bibliographic Details
Main Authors: Chen, Suchang, Guo, Daqiang
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.11275
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915671057629184
author Chen, Suchang
Guo, Daqiang
author_facet Chen, Suchang
Guo, Daqiang
contents Existing pipelines for vision-language models (VLMs) in robotic manipulation prioritize broad semantic generalization from images and language, but typically omit execution-critical parameters required for contact-rich actions in manufacturing cells. We formalize an object-centric manipulation-logic schema, serialized as an eight-field tuple τ, which exposes object, interface, trajectory, tolerance, and force/impedance information as a first-class knowledge signal between human operators, VLM-based assistants, and robot controllers. We instantiate τ and a small knowledge base (KB) on a 3D-printer spool-removal task in a collaborative cell, and analyze τ-conditioned VLM planning using plan-quality metrics adapted from recent VLM/LLM planning benchmarks, while demonstrating how the same schema supports taxonomy-tagged data augmentation at training time and logic-aware retrieval-augmented prompting at test time as a building block for assistant systems in smart manufacturing enterprises.
format Preprint
id arxiv_https___arxiv_org_abs_2512_11275
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Towards Logic-Aware Manipulation: A Knowledge Primitive for VLM-Based Assistants in Smart Manufacturing
Chen, Suchang
Guo, Daqiang
Robotics
Existing pipelines for vision-language models (VLMs) in robotic manipulation prioritize broad semantic generalization from images and language, but typically omit execution-critical parameters required for contact-rich actions in manufacturing cells. We formalize an object-centric manipulation-logic schema, serialized as an eight-field tuple τ, which exposes object, interface, trajectory, tolerance, and force/impedance information as a first-class knowledge signal between human operators, VLM-based assistants, and robot controllers. We instantiate τ and a small knowledge base (KB) on a 3D-printer spool-removal task in a collaborative cell, and analyze τ-conditioned VLM planning using plan-quality metrics adapted from recent VLM/LLM planning benchmarks, while demonstrating how the same schema supports taxonomy-tagged data augmentation at training time and logic-aware retrieval-augmented prompting at test time as a building block for assistant systems in smart manufacturing enterprises.
title Towards Logic-Aware Manipulation: A Knowledge Primitive for VLM-Based Assistants in Smart Manufacturing
topic Robotics
url https://arxiv.org/abs/2512.11275