UAV swarm communication middleware improves real-time visual data sharing
Perception-Aware Communication Middleware for Distributed Visual Perception in UAV Swarms
Multiagent Systems
Summary
UAV swarms often need to share images and videos quickly to find objects or detect dangers. The authors designed special software that helps these drones send complete and clear images to each other fast, even with limited wireless connections. This software sorts data by importance and checks that images are good enough for the drones' AI to recognize objects properly. Their tests showed faster and smarter handling of visual data, helping drones work better together in real time.
What this means in practice
- •For drone fleet operators: Improve drone-to-drone image sharing to ensure timely and reliable object detection for safety-critical missions.
- •For wireless network engineers: Develop communication software that prioritizes complete visual data over raw packets to optimize bandwidth for distributed AI applications.
Authors
Manveen Kaur, Kevin Loi, Ifunanya Okafor, Daniel Ng, Joseph Lucey-Renteria
Abstract
Unmanned Aerial Vehicle (UAV) swarms increasingly support safety-critical applications that rely on distributed visual perception. Meeting the low-latency requirements of these applications can require perception models to execute within the swarm on inference-capable UAVs, creating a need for efficient UAV-to-UAV transport of high-bandwidth perception data. However, the Quality-of-Service (QoS) requirements of perception differ from conventional packet-level QoS; successful delivery of individual packets does not ensure that a complete, timely, and usable image is available for inference. We present a novel perception-aware communication middleware that treats complete perception-data samples as the communication objects for which QoS must be satisfied. The middleware extends a lightweight UDP broker-based publish-subscribe architecture with perception-specific services, including image fragmentation and reconstruction, concurrent packet transmission, priority-aware scheduling, and image quality assessment. The middleware is evaluated on a heterogeneous hardware testbed emulating a UAV swarm using YOLOv8n object detection. Experimental results demonstrate low end-to-end application latency, substantially higher throughput than a lightweight UDP broker, effective prioritization of perception traffic under increasing background load, and mitigation of object-detection degradation through middleware-level image quality assessment. This work provides an initial framework for integrating AI-specific data handling into communication middleware to support emerging distributed AI applications in multi-agent mobile cyber-physical systems.