Multimodal Large Language Models for Real-Time Situated Reasoning

TL;DR

This paper demonstrates how multimodal large language models, combined with robotic platforms, can support real-time, context-aware decision-making in domestic environments, emphasizing reasoning about social norms and user preferences.

Contribution

It introduces a system integrating GPT-4o with a TurtleBot 4 to enable real-time situated reasoning based on visual input in a home setting.

Findings

Effective environment evaluation through vision input

Ability to reason about social norms and user preferences

Highlighting challenges in real-time performance and bias

Abstract

In this work, we explore how multimodal large language models can support real-time context- and value-aware decision-making. To do so, we combine the GPT-4o language model with a TurtleBot 4 platform simulating a smart vacuum cleaning robot in a home. The model evaluates the environment through vision input and determines whether it is appropriate to initiate cleaning. The system highlights the ability of these models to reason about domestic activities, social norms, and user preferences and take nuanced decisions aligned with the values of the people involved, such as cleanliness, comfort, and safety. We demonstrate the system in a realistic home environment, showing its ability to infer context and values from limited visual input. Our results highlight the promise of multimodal large language models in enhancing robotic autonomy and situational awareness, while also underscoring challenges related to consistency, bias, and real-time performance.