STEP: State-Aware Task Estimation and Planning with Multi-Modal LLMs for Human-Robot Collaboration

2026-08-27

AI Summary

为解决多模态大语言模型在人机协作任务规划中缺乏状态理解和执行模糊问题，提出STEP方法，通过预测系统状态转换来提高计划的可执行性和准确性。

Abstract

Effective human-robot collaboration in industrial settings requires robots to understand human intentions and assist with task planning, reducing workload. Recent works have explored the use of Multi-modal Large Language Models (MM-LLMs) for task planning in such data-scarce scenarios, leveraging in-context learning to interpret user actions and generate long-horizon action plans in natural language. However, MM-LLMs inherently lack an understanding of system states and do not track state transitions, often leading to hallucinated actions that deviate from the intended goal. Additionally, generating action plans in natural language tends to limit the generated plans to a high level, introducing ambiguity in action execution. To address these limitations, we propose the State-aware Task Estimator and Planner (STEP), which prompts a MM-LLM to explicitly estimate the state of the system and predict the state transitions resulting from executed actions. By forecasting future states alongside actions, STEP ensures task-convergent planning while also providing additional assistance parameters necessary for executing the predicted actions. We evaluate STEP in a simulated environment using a robot assembly task. Our approach outperforms the state-of-the-art by 32.8% in action executability and 14.8% in final-state error.

Problem

• human-robot collaboration
• task planning
• system states
• state transitions
• action executability

Innovation

• State-aware Task Estimation
• Multi-Modal Large Language Models
• Task Planning
• Human-Robot Collaboration
• State Transitions