A3VLM: Actionable Articulation-Aware Vision Language Model

TL;DR

A3VLM is a novel vision language model that emphasizes object articulation and action affordances, enabling robot-agnostic manipulation and navigation tasks with reduced data collection needs.

Contribution

It introduces an object-centric, articulation-aware VLM that is robot-agnostic and can be translated into robot actions using simple primitives, addressing data collection challenges.

Findings

Effective in simulation benchmarks

Demonstrates stability in real-world settings

Reduces need for robot interaction data

Abstract

Vision Language Models (VLMs) have received significant attention in recent years in the robotics community. VLMs are shown to be able to perform complex visual reasoning and scene understanding tasks, which makes them regarded as a potential universal solution for general robotics problems such as manipulation and navigation. However, previous VLMs for robotics such as RT-1, RT-2, and ManipLLM have focused on directly learning robot-centric actions. Such approaches require collecting a significant amount of robot interaction data, which is extremely costly in the real world. Thus, we propose A3VLM, an object-centric, actionable, articulation-aware vision language model. A3VLM focuses on the articulation structure and action affordances of objects. Its representation is robot-agnostic and can be translated into robot actions using simple action primitives. Extensive experiments in both simulation benchmarks and real-world settings demonstrate the effectiveness and stability of A3VLM. We release our code and other materials at https://github.com/changhaonan/A3VLM.