Automation of logistics enhances efficiency, reduces costs, and minimizes human error. Image processing—particularly vision-based AI—enables real-time tracking, object recognition, and intelligent decision-making, thereby improving supply chain resilience. This study addresses the challenge of deploying deep learning-based object detection on resource-constrained embedded platforms, such as NVIDIA Jetson devices on UAVs and ground robots, for real-time logistics applications. Specifically, we provide a comprehensive comparative analysis of YOLOv5 and YOLOv8, evaluating their performance in terms of inference speed, accuracy, and dataset-specific metrics using both the Common Objects in Context (COCO) dataset and a novel, custom logistics dataset tailored for aerial and ground-based logistics scenarios. A key contribution is the development of a user-friendly graphical user interface (GUI) for selective object visualization, enabling dynamic interaction and real-time filtering of detection results—significantly enhancing practical usability. Furthermore, we investigate and compare deployment strategies in both Python 3.9 and C# (ML. NET v3 and .NET Framework 7) environments, highlighting their respective impacts on performance and scalability. This research offers valuable insights and practical guidelines for optimizing real-time object detection deployment on embedded platforms in UAV- and ground robot-based logistics, with a focus on efficient resource utilization and enhanced operational effectiveness.

Industrial environments are complex, making the monitoring of gauge meters challenging. This is especially true in confined spaces, underground, or at high altitudes. These difficulties underscore the need for intelligent solutions in the inspection and monitoring of plant assets, such as gauge meters. In this study, we plan to integrate unmanned ground vehicles and unmanned aerial vehicles to address the challenge, but the integration of these heterogeneous systems introduces additional complexities in terms of coordination, interoperability, and communication. Our goal is to develop a multi-domain robotic swarm system for industrial mapping and asset monitoring. We created an experimental setup to simulate industrial inspection tasks, involving the integration of a TurtleBot 2 and a QDrone 2. The TurtleBot 2 utilizes simultaneous localization and mapping (SLAM) technology, along with a LiDAR sensor, for mapping and navigation purposes. The QDrone 2 captures high-resolution images of meter gauges. We evaluated the system’s performance in both simulation and real-world environments. The system achieved accurate mapping, high localization, and landing precision, with 84% accuracy in detecting meter gauges. It also reached 87.5% accuracy in reading gauge indicators using the paddle OCR algorithm. The system navigated complex environments effectively, showcasing the potential for real-time collaboration between ground and aerial robotic platforms.