LIT: Large Language Model Driven Intention Tracking for Proactive Human-Robot Collaboration -- A Robot Sous-Chef Application

TL;DR

This paper introduces LIT, a method using large language and vision models to predict human intentions in long-term collaborative tasks, enabling proactive robot assistance in cooking scenarios.

Contribution

The paper presents a novel intention tracking approach that leverages LLMs and VLMs for proactive human-robot collaboration in long-horizon tasks.

Findings

Effective prediction of human intentions in collaborative tasks

Smooth coordination demonstrated in cooking scenarios

Proactive robot assistance improves collaboration efficiency

Abstract

Large Language Models (LLM) and Vision Language Models (VLM) enable robots to ground natural language prompts into control actions to achieve tasks in an open world. However, when applied to a long-horizon collaborative task, this formulation results in excessive prompting for initiating or clarifying robot actions at every step of the task. We propose Language-driven Intention Tracking (LIT), leveraging LLMs and VLMs to model the human user's long-term behavior and to predict the next human intention to guide the robot for proactive collaboration. We demonstrate smooth coordination between a LIT-based collaborative robot and the human user in collaborative cooking tasks.