Abstract
Telecommunications and computer vision solutions have evolved significantly in recent years, allowing a huge advance in the functionalities and applications offered. However, these two fields have been making their way as separate areas, not exploring the potential benefits of merging the innovations brought from each of them. In challenging environments, for example, combining radio sensing and computer vision can strongly contribute to solving problems such as those introduced by obstructions or limited lighting. Machine learning algorithms, able to fuse heterogeneous and multi-modal data, are also a key element for understanding and inferring additional knowledge from raw and low-level data, able to create a new abstracting level that can significantly enhance many applications. This paper introduces the CONVERGE vision-radio concept, a new paradigm that explores the benefits of integrating two fields of knowledge towards the vision of View-to-Communicate, Communicate-to-View. The main concepts behind this vision, including supporting use cases and the proposed architecture, are presented. CONVERGE introduces a set of tools integrating wireless communications and computer vision to create a novel experimental infrastructure that will provide open datasets to the scientific community of both experimental and simulated data, enabling new research addressing various 6 G verticals, including telecommunications, automotive, manufacturing, media, and health.

Abstract

Abstract
The increasing complexity of wireless environments, driven by user mobility and dynamic obstructions, poses significant challenges to maintaining Line-of-Sight (LoS) connectivity. Mobile base stations (gNBs) offer a promising solution by physically relocating to restore or sustain LoS. This paper explores how reinforcement learning (RL) can be applied to gNB mobility control within vision-aided network systems. As part of the CONVERGE project, we present the CONVERGE Chamber Simulator (CC-SIM), a 3D environment for developing, training, and testing gNB mobility control algorithms. CC-SIM models user and obstacle mobility, visual occlusion, and Radio Frequency (RF) propagation while supporting both offline reinforcement learning and real-time validation through integration with OpenAirInterface (OAI). Leveraging CC-SIM, we trained a Deep Q-Network (DQN) agent that proactively repositions gNBs under dynamic conditions. Across three representative use cases, the agent reduced LoS blockage by up to 42% compared to static deployments, highlighting the potential of RL-driven mobility control and positioning CC-SIM as a practical platform for advancing adaptive, next-generation wireless networks.

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 to support vehicular users and Vehicle-to-Everything (V2X) applications. 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. Existing approaches rely on probabilistic blockage models or require dedicated infrastructure such as Reconfigurable Intelligent Surfaces. This paper proposes VTOPA, a Vision-Aided Traffic- and Obstacle-Aware Positioning Algorithm that complements these approaches by autonomously extracting environmental information - such as obstacle geometries and UE locations - via computer vision, enabling infrastructure-free deployment. The algorithm employs Particle Swarm Optimization to determine UAV positions that maximize aggregate throughput while prioritizing LoS connectivity and accounting for heterogeneous traffic demands. VTOPA is particularly suited for rapid deployment scenarios such as emergency response and temporary events. Evaluated through simulations in ns-3, VTOPA achieves up to 50% increase in aggregate throughput and 50% reduction in delay, outperforming state of the art benchmarks in obstacle-rich environments. © 2026 The Authors.

Abstract
Unmanned Aerial Vehicles (UAVs) are a promising solution for next-generation wireless networks due to their mobility, rapid deployment, and ability to provide Line-of-Sight (LoS) connectivity. However, deploying multiple UAVs in realt-ime to meet dynamic, non-uniform traffic demands remains a significant challenge, especially when aiming to optimize network throughput and resource utilization. In this paper, we propose the Efficient Multi-UAV Traffic-Aware Deployment (EMTAD) algorithm, a scalable algorithm that jointly minimizes UAV count and optimizes 3D positioning based on real-time user distribution and traffic demand. In contrast to prior works that assume static user patterns or fixed UAV counts, EMTAD dynamically adapts UAV deployment to maximize spectral efficiency and satisfy user-specific Quality of Service (QoS) requirements. Simulation results demonstrate that EMTAD reduces the number of UAVs required and achieves superior aggregate throughput compared to baseline approaches.