Simulation experiments on the feasibility of replacing human observers in E-VLOS UAV flights with Unoccupied Ground Vehicle units

Extended Visual Line of Sight (E-VLOS) operations are increasingly viewed as a practical intermediate step toward scalable Beyond Visual Line of Sight (BVLOS) unoccupied aerial vehicle (UAV) deployments. However, current E-VLOS practices rely heavily on human observers, introducing limitations in scalability, cost, consistency, and measurable performance assurance. This study investigates the feasibility of replacing human E-VLOS observers with an autonomous unoccupied ground vehicle (UGV) unit equipped with vision-based perception. A heterogeneous UAV-UGV simulation framework is shown in which a visionequipped UGV autonomously tracks and observes a UAV using only monocular visual feedback, without access to UAV state information or telemetry. The system is implemented in a physicsbased simulation environment. It employs a closed-loop visionbased control strategy to maintain continuous visual contact, regulate relative distance, and recover from temporary loss of visibility. Performance is evaluated using metrics directly aligned with E-VLOS observer responsibilities, including visual contact persistence, tracking stability, distance regulation, robustness to target loss, and control effort. Experimental results demonstrate that the UGV maintains persistent situational awareness, exhibits stable and conservative observer behavior, and reliably reacquires the UAV following brief visibility disruptions. The findings suggest that autonomous ground observers can fulfill key functional roles of human E-VLOS participants while offering improved scalability, repeatability, and quantitative performance verification. This work presents a structured simulation pipeline and empirical evidence supporting heterogeneous robotic observers as a viable pathway toward resilient, certifiable BVLOS UAV operations.