Autonomous Vision-Aided UAV Positioning for Obstacle-Aware Wireless Connectivity

2025-06-29

AI Summary

To address frequent line-of-sight (LoS) link disruptions between unmanned aerial vehicles (UAVs) and ground user equipment (UEs) caused by dense urban obstacles, this paper proposes a vision-aided autonomous UAV positioning algorithm. The method integrates real-time computer vision–based perception (for obstacle and UE localization), LoS feasibility assessment, and dynamic optimization to enable online UAV deployment decisions. Within an ns-3 simulation framework, it jointly models communication traffic, environmental constraints, and service fairness. Its key innovation lies in the first-ever co-optimization of visual perception with multi-dimensional network metrics—namely, throughput, end-to-end latency, and Pareto fairness. Evaluated in complex urban scenarios, the approach achieves a 50% increase in aggregate throughput, a 50% reduction in end-to-end latency, and maintains Pareto fairness—outperforming all baseline methods across all metrics.

Technology Category

• Search and Optimization: Algorithm Configuration
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Computer Vision: Learning & Optimization for CV

Application Category

• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments

Abstract

Unmanned Aerial Vehicles (UAVs) offer a promising solution for enhancing wireless connectivity and Quality of Service (QoS) in urban environments, acting as aerial Wi-Fi access points or cellular base stations. Their flexibility and rapid deployment capabilities make them suitable for addressing infrastructure gaps and traffic surges. However, optimizing UAV positions to maintain Line of Sight (LoS) links with ground User Equipment (UEs) remains challenging in obstacle-dense urban scenarios. This paper proposes VTOPA, a Vision-Aided Traffic- and Obstacle-Aware Positioning Algorithm that autonomously extracts environmental information -- such as obstacles and UE locations -- via computer vision and optimizes UAV positioning accordingly. The algorithm prioritizes LoS connectivity and dynamically adapts to user traffic demands in real time. Evaluated through simulations in ns-3, VTOPA achieves up to a 50% increase in aggregate throughput and a 50% reduction in delay, without compromising fairness, outperforming benchmark approaches in obstacle-rich environments.

Problem

• Optimizing UAV positions for Line of Sight in urban areas
• Autonomous obstacle and user location detection via computer vision
• Real-time adaptation to user traffic demands for connectivity

Innovation

• Vision-aided obstacle and UE detection
• Real-time adaptive UAV positioning
• LoS connectivity optimization algorithm