cs.ROMar 5, 2026

LLM-Guided Decentralized Exploration with Self-Organizing Robot Teams

Authors: Hiroaki Kawashima, Shun Ikejima, Takeshi Takai, Mikita Miyaguchi, Yasuharu Kunii

Organizations: Graduate School of Information Science, University of Hyogo, Hyogo, Japan · School of Social Information Science, University of Hyogo, Hyogo, Japan · Takenaka Research & Development Institute, Takenaka Corporation, Chiba, Japan · Faculty of Science and Engineering, Chuo University, Tokyo, Japan

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

When individual robots have limited sensing capabilities or insufficient fault tolerance, it becomes necessary for multiple robots to form teams during exploration, thereby increasing the collective observation range and reliability. Traditionally, swarm formation has often been managed by a central controller; however, from the perspectives of robustness and flexibility, it is preferable for the swarm to operate autonomously even in the absence of centralized control. In addition, the determination of exploration targets for each team is crucial for efficient exploration in such multi-team exploration scenarios. This study therefore proposes an exploration method that combines (1) an algorithm for self-organization, enabling the autonomous and dynamic formation of multiple teams, and (2) an algorithm that allows each team to autonomously determine its next exploration target (destination). In particular, for (2), this study explores a novel strategy based on large language models (LLMs), while classical frontier-based methods and deep reinforcement learning approaches have been widely studied. The effectiveness of the proposed method was validated through simulations involving tens to hundreds of robots.

Figures & tables

Figure 1: Sensor model and occupancy grid map generation. In (b), occupancy probability values are indicated in grayscale: gray cells represent unexplored areas, white cells represent explored free areas (free space), and black cells represent explored areas with obstacles (occupied space). Green cells represent frontier cells.
Figure 2: Example of self-organized teams and a charging robot
Figure 3: Example exploration using the baseline method
Figure 4: Comparison of explored area between baseline and LLM-based methods (N = 15)
Figure 5: Example of LLM reasoning for destination selection
Figure 6: Comparison of target cell statistics between baseline and LLM-based methods
Figure 7: Exploration with autonomous team formation with N=50N=50 . The bright areas represent explored regions and the small red dots correspond to individual robots.
Figure 8: A screenshot of the LLM-based exploration simulation with N=100N=100
More in this topic

Multi-Robot Exploration

Multi-robot exploration coordinates robot teams to map unknown environments, find targets, and gather information efficiently and safely.

See all 52 papers

Explore similar work

CardsList

  1. LLM-Foraging: Large Language Models for Decentralized Swarm Robot Foraging

    May 2, 2026Peihan Li, Joanna Gutierrez, Fabian Hernandez +2Swarm RoboticsLanguage Model-Based Control

    Drexel University, Philadelphia, PA 19104, USA · The University of Texas Rio Grande Valley, Edinburg, Texas 78541, USA

  2. Autonomous Frontier-Based Exploration with VLM Guidance

    May 22, 2026Aarush Aitha, Avideh ZakhorMobile RoboticsFrontier-Based Exploration

    EECS Department, University of California

  3. EFLUX: Elastic Multi-Robot Formation Navigation and Adaptation with Agentic LLMs

    Jul 13, 2026Jinyuan Zhang, Yuwei Wu, Guangyao Shi +3Multi-Robot Formation ControlMulti-Robot Motion Planning

    GRASP Lab, University of Pennsylvania, Philadelphia, PA 19104, USA · Department of Computer Science, University of Southern California, Los Angeles, CA 90089, USA