Zero-shot adaptable task planning for autonomous construction robots: a comparative study of lightweight single and multi-AI agent systems

TL;DR

This paper investigates lightweight foundation models for adaptable task planning in construction robots, demonstrating that multi-agent systems outperform GPT-4o in cost and generalizability across various construction roles.

Contribution

It introduces and evaluates four lightweight AI models, including multi-agent teams, for flexible and cost-effective task planning in construction robotics, advancing beyond current state-of-the-art methods.

Findings

Multi-agent teams outperform GPT-4o in most metrics.

Teams with three and four agents show better generalizability.

The four-agent team is ten times more cost-effective.

Abstract

Robots are expected to play a major role in the future construction industry but face challenges due to high costs and difficulty adapting to dynamic tasks. This study explores the potential of foundation models to enhance the adaptability and generalizability of task planning in construction robots. Four models are proposed and implemented using lightweight, open-source large language models (LLMs) and vision language models (VLMs). These models include one single agent and three multi-agent teams that collaborate to create robot action plans. The models are evaluated across three construction roles: Painter, Safety Inspector, and Floor Tiling. Results show that the four-agent team outperforms the state-of-the-art GPT-4o in most metrics while being ten times more cost-effective. Additionally, teams with three and four agents demonstrate the improved generalizability. By discussing how agent behaviors influence outputs, this study enhances the understanding of AI teams and supports future research in diverse unstructured environments beyond construction.