Text to Robotic Assembly of Multi Component Objects using 3D Generative AI and Vision Language Models

TL;DR

This paper introduces a pipeline combining 3D generative AI and vision-language models to enable robots to assemble multi-component objects from text prompts, with high user preference and interactive refinement.

Contribution

It presents a novel integration of 3D generative AI and VLMs for multi-component object assembly, including zero-shot reasoning and user-in-the-loop refinement.

Findings

VLM accurately identifies mesh regions for component assignment 90.6% of the time

User preference for VLM-generated assignments is significantly higher than rule-based or random methods

System supports conversational feedback for improved human control

Abstract

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.