LLM-Based Semantic Navigation on a Low-Cost ROS Mobile Robot: A Hybrid Edge–Cloud Architecture

Abstract

Autonomous mobile robots require robust perception and high-level reasoning to operate in complex indoor environments. While the Robot Operating System (ROS) provides a modular framework for mapping and navigation, classical pipelines lack semantic understanding and natural-language interaction. This paper presents a semantic-aware autonomous navigation framework implemented on a ROS 1 (Melodic) mobile robot equipped with a two-dimensional light detection and ranging (LiDAR) sensor and an RGB-D camera. The system integrates LiDAR-based simultaneous localization and mapping (SLAM), the ROS navigation stack (move_base), and a lightweight You Only Look Once (YOLO) object detector for real-time on-board perception, and it anchors detections into the metric map to build a semantic map. A large language model (LLM) interprets natural-language instructions and converts them into structured navigation goals. Perception and control run entirely on-board the Jetson Nano, whereas the LLM is invoked episodically as a cloud service, yielding a hybrid embedded/cloud architecture. In indoor trials over a semantic map of two object classes, the system grounded all ten multilingual commands to the correct objects at a reasoning cost of about one second, and safely rejected a command referring to an unmapped object. We present this as an in-depth single-platform case study: owing to the 4 GB memory budget, the on-board detector and the full navigation stack are time-multiplexed rather than run continuously in parallel; nonetheless, a single degraded end-to-end trial confirmed that perception, online semantic anchoring, language grounding, and navigation compose within one continuous session. The framework offers a low-cost, extensible basis for language-guided robots in smart environments.