Discovering Object Attributes by Prompting Large Language Models With Perception-Action Apis

Abstract

There has been a lot of interest in grounding natural language to physical entities through visual context. While Vision Language Models (VLMs) can ground linguistic instructions to visual sensory information, they struggle with grounding non-visual attributes, like the weight of an object. Our key insight is that non-visual attribute detection can be effectively achieved by active perception guided by visual reasoning. To this end, we present a perception-action API that consists of VLMs and Large Language Models (LLMs) as backbones, together with a set of robot control functions. When prompted with this API and a natural language query, an LLM generates a program to actively identify attributes given an input image. Offline testing on the Odd-One-Out (<tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{O}^{\mathbf{3}}$</tex>) dataset demonstrates that our framework outperforms vanilla VLMs in detecting attributes like relative object location, size, and weight. Online testing in realistic household scenes on AI2THOR and a real robot demonstration on a DJI RoboMaster EP robot highlight the efficacy of our approach.