Task-Aware Positioning for Improvisational Tasks in Mobile Construction Robots via an AI Agent with Multi-LMM Modules

TL;DR

This paper introduces a multi-modal AI agent for mobile construction robots that understands improvisational tasks from natural language, identifies task locations, and positions itself accordingly, enhancing autonomous task handling in dynamic construction environments.

Contribution

The study presents a novel AI agent with multi-LMM modules that interpret natural language tasks and autonomously position mobile robots in improvisational construction scenarios.

Findings

92.2% success rate in identifying task locations

Effective handling of improvisational tasks in construction

Integration of multi-modal models for task understanding

Abstract

Due to the ever-changing nature of construction, many tasks on sites occur in an improvisational manner. Existing mobile construction robot studies remain limited in addressing improvisational tasks, where task-required locations, timing of task occurrence, and contextual information required for task execution are not known in advance. We propose an agent that understands improvisational tasks given in natural language, identifies the task-required location, and positions itself. The agent's functionality was decomposed into three Large Multimodal Model (LMM) modules operating in parallel, enabling the application of LMMs for task interpretation and breakdown, construction drawing-based navigation, and visual reasoning to identify non-predefined task-required locations. The agent was implemented with a quadruped robot and achieved a 92.2% success rate for identifying and positioning at task-required locations across three tests designed to assess improvisational task handling. This study enables mobile construction robots to perform non-predefined tasks autonomously.