Adaptive Attention-Based Model for 5G Radio-based Outdoor Localization

2025-03-31

AI Summary

To address degraded positioning accuracy in dynamic 5G urban and vehicular environments—caused by multipath interference and occlusions—this paper proposes an adaptive attention framework. The method integrates a suite of three lightweight, specialized positioning models, jointly optimized for accuracy, latency, and robustness, with a single-layer perceptron (SLP)-based dynamic routing mechanism that enables real-time, environment-aware model selection. We introduce the first input-feature-driven multi-expert attention architecture, employing a shallow attention network trained on massive MIMO measurement data. Evaluated on real-world vehicle positioning datasets, our framework reduces mean positioning error by 37% compared to general-purpose models, achieves inference latency under 8 ms, and maintains an average model size of only 42 KB—demonstrating significant improvements in both accuracy and efficiency for edge-deployable 5G positioning systems.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Machine Learning: Learning on the Edge & Model Compression
• Search and Optimization: Learning to Search

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Radio-based localization in dynamic environments, such as urban and vehicular settings, requires systems that can efficiently adapt to varying signal conditions and environmental changes. Factors such as multipath interference and obstructions introduce different levels of complexity that affect the accuracy of the localization. Although generalized models offer broad applicability, they often struggle to capture the nuances of specific environments, leading to suboptimal performance in real-world deployments. In contrast, specialized models can be tailored to particular conditions, enabling more precise localization by effectively handling domain-specific variations and noise patterns. However, deploying multiple specialized models requires an efficient mechanism to select the most appropriate one for a given scenario. In this work, we develop an adaptive localization framework that combines shallow attention-based models with a router/switching mechanism based on a single-layer perceptron (SLP). This enables seamless transitions between specialized localization models optimized for different conditions, balancing accuracy, computational efficiency, and robustness to environmental variations. We design three low-complex localization models tailored for distinct scenarios, optimized for reduced computational complexity, test time, and model size. The router dynamically selects the most suitable model based on real-time input characteristics. The proposed framework is validated using real-world vehicle localization data collected from a massive MIMO base station (BS), demonstrating its ability to seamlessly adapt to diverse deployment conditions while maintaining high localization accuracy.

Problem

• Adaptive localization for dynamic 5G outdoor environments
• Handling multipath interference and signal obstructions
• Dynamic model selection for varying environmental conditions

Innovation

• Adaptive attention-based model for 5G localization
• Router mechanism with single-layer perceptron
• Low-complex models for diverse scenarios