Text to Robotic Assembly of Multi Component Objects using 3D Generative AI and Vision Language Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915634354323456 |
|---|---|
| author | Kyaw, Alexander Htet Gupta, Richa Shah, Dhruv Sinha, Anoop Mathewson, Kory Pender, Stefanie Chitta, Sachin Koga, Yotto Ahmed, Faez Sass, Lawrence Davis, Randall |
| author_facet | Kyaw, Alexander Htet Gupta, Richa Shah, Dhruv Sinha, Anoop Mathewson, Kory Pender, Stefanie Chitta, Sachin Koga, Yotto Ahmed, Faez Sass, Lawrence Davis, Randall |
| contents | Advances in 3D generative AI have enabled the creation of physical objects from text prompts, but challenges remain in creating objects involving multiple component types. We present a pipeline that integrates 3D generative AI with vision-language models (VLMs) to enable the robotic assembly of multi-component objects from natural language. Our method leverages VLMs for zero-shot, multi-modal reasoning about geometry and functionality to decompose AI-generated meshes into multi-component 3D models using predefined structural and panel components. We demonstrate that a VLM is capable of determining which mesh regions need panel components in addition to structural components, based on the object's geometry and functionality. Evaluation across test objects shows that users preferred the VLM-generated assignments 90.6% of the time, compared to 59.4% for rule-based and 2.5% for random assignment. Lastly, the system allows users to refine component assignments through conversational feedback, enabling greater human control and agency in making physical objects with generative AI and robotics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_02162 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Text to Robotic Assembly of Multi Component Objects using 3D Generative AI and Vision Language Models Kyaw, Alexander Htet Gupta, Richa Shah, Dhruv Sinha, Anoop Mathewson, Kory Pender, Stefanie Chitta, Sachin Koga, Yotto Ahmed, Faez Sass, Lawrence Davis, Randall Robotics Artificial Intelligence Human-Computer Interaction Advances in 3D generative AI have enabled the creation of physical objects from text prompts, but challenges remain in creating objects involving multiple component types. We present a pipeline that integrates 3D generative AI with vision-language models (VLMs) to enable the robotic assembly of multi-component objects from natural language. Our method leverages VLMs for zero-shot, multi-modal reasoning about geometry and functionality to decompose AI-generated meshes into multi-component 3D models using predefined structural and panel components. We demonstrate that a VLM is capable of determining which mesh regions need panel components in addition to structural components, based on the object's geometry and functionality. Evaluation across test objects shows that users preferred the VLM-generated assignments 90.6% of the time, compared to 59.4% for rule-based and 2.5% for random assignment. Lastly, the system allows users to refine component assignments through conversational feedback, enabling greater human control and agency in making physical objects with generative AI and robotics. |
| title | Text to Robotic Assembly of Multi Component Objects using 3D Generative AI and Vision Language Models |
| topic | Robotics Artificial Intelligence Human-Computer Interaction |
| url | https://arxiv.org/abs/2511.02162 |