Research

Paper

AI LLM March 24, 2026

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

Authors

Seongju Jang, Francis Baek, SangHyun Lee

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.

Metadata

arXiv ID: 2603.22903
Provider: ARXIV
Primary Category: cs.RO
Published: 2026-03-24
Fetched: 2026-03-25 06:02

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.22903v1</id>\n    <title>Task-Aware Positioning for Improvisational Tasks in Mobile Construction Robots via an AI Agent with Multi-LMM Modules</title>\n    <updated>2026-03-24T07:51:32Z</updated>\n    <link href='https://arxiv.org/abs/2603.22903v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.22903v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>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.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.RO'/>\n    <published>2026-03-24T07:51:32Z</published>\n    <arxiv:primary_category term='cs.RO'/>\n    <author>\n      <name>Seongju Jang</name>\n    </author>\n    <author>\n      <name>Francis Baek</name>\n    </author>\n    <author>\n      <name>SangHyun Lee</name>\n    </author>\n  </entry>"
}