Object search in large-scale, unstructured environments remains a fundamental challenge in robotics, particularly in dynamic or expansive settings such as outdoor autonomous exploration. This task requires robust spatial reasoning and the ability to leverage prior experiences. While Large Language Models (LLMs) offer strong semantic capabilities, their application in embodied contexts is limited by a grounding gap in spatial reasoning and insufficient mechanisms for memory integration and decisionthis http URLaddress these challenges, we propose GET (Goal-directed Exploration and Targeting), a framework that enhances object search by combining LLM-based reasoning with experience-guided exploration. At its core is DoUT (Diagram of Unified Thought), a reasoning module that facilitates real-time decision-making through a role-based feedback loop, integrating task-specific criteria and external memory. For repeated tasks, GET maintains a probabilistic task map based on a Gaussian Mixture Model, allowing for continual updates to object-location priors as environmentsthis http URLconducted in real-world, large-scale environments demonstrate that GET improves search efficiency and robustness across multiple LLMs and task settings, significantly outperforming heuristic and LLM-only baselines. These results suggest that structured LLM integration provides a scalable and generalizable approach to embodied decision-making in complex environments.
View on arXiv@article{zheng2025_2505.20828,
title={ GET: Goal-directed Exploration and Targeting for Large-Scale Unknown Environments },
author={ Lanxiang Zheng and Ruidong Mei and Mingxin Wei and Hao Ren and Hui Cheng },
journal={arXiv preprint arXiv:2505.20828},
year={ 2025 }
}