UniAff: A Unified Representation of Affordances for Tool Usage and Articulation with Vision-Language Models

TL;DR

UniAff introduces a unified framework combining 3D object manipulation and task understanding, leveraging multi-modal language models and a new dataset to enhance robotic manipulation of tools and articulated objects.

Contribution

It presents a comprehensive paradigm and dataset for unified robotic manipulation, integrating affordance recognition and 3D motion reasoning with vision-language models.

Findings

Significantly improves generalization in robotic manipulation tasks.

Demonstrates effectiveness in both simulation and real-world environments.

Provides a new dataset and baseline for future research.

Abstract

Previous studies on robotic manipulation are based on a limited understanding of the underlying 3D motion constraints and affordances. To address these challenges, we propose a comprehensive paradigm, termed UniAff, that integrates 3D object-centric manipulation and task understanding in a unified formulation. Specifically, we constructed a dataset labeled with manipulation-related key attributes, comprising 900 articulated objects from 19 categories and 600 tools from 12 categories. Furthermore, we leverage MLLMs to infer object-centric representations for manipulation tasks, including affordance recognition and reasoning about 3D motion constraints. Comprehensive experiments in both simulation and real-world settings indicate that UniAff significantly improves the generalization of robotic manipulation for tools and articulated objects. We hope that UniAff will serve as a general baseline for unified robotic manipulation tasks in the future. Images, videos, dataset, and code are published on the project website at:https://sites.google.com/view/uni-aff/home