Exploring the Feasibility of Autonomous Vehicle Sensor Suites for Roadway Lighting Evaluation

Autonomous vehicles are increasingly equipped with advanced multi-sensor suites, such as high-resolution cameras, LiDAR, radar, and GNSS/IMU fusion, that provide continuous and high-fidelity perception of the driving environment. While these systems are primarily designed for navigation and safety, they also offer new opportunities for infrastructure monitoring. This paper investigates the feasibility of using autonomous vehicle perception systems to evaluate roadway lighting conditions, which are critical factor influencing nighttime visibility, safety, and energy efficiency. The study examines both technical and operational feasibility. The technical assessment focuses on sensor calibration, multimodal data fusion, and geolocation accuracy, while the operational evaluation considers scalability across AV fleets, real-time edge and cloud processing, cost efficiency, and data governance. Relevant standards, including ISO 21448, IEEE P2020, and ISO 34503, are reviewed to contextualize the role of AV sensing in infrastructure monitoring. Comparative analysis highlights how AV-based roadway lighting assessment differs from conventional approaches. Potential applications include adaptive streetlight control, predictive maintenance, and integration with digital twins. The findings suggest that autonomous vehicles can serve as mobile infrastructure auditors, enabling continuous, automated, and data-driven monitoring for intelligent transportation systems and future smart cities.