Road Surface Condition Inspection Using a Laser Scanner Mounted on an Autonomous Driving Car

摘要

Inspection and repair of road infrastructures are important for safety. While highways and motorways are periodically inspected with specialized vehicles, the roads which are maintained by local governments are not inspected because of lack of budget and workforce. In the future, however, a large number of autonomous driving cars will run everywhere. They are equipped with laser scanners to recognize the surroundings. If we utilize these sensors to inspect the road surface condition automatically, the cost of inspection will be reduced dramatically. In this paper, we extract transverse profiles of a road using point clouds which are recorded by a laser scanner mounted on an autonomous driving car. Point clouds are converted to the same format of special vehicle. We compared the data recorded by a specialized vehicle and a car with a laser scanner in Ichinomiya, Aichi prefecture, Japan and found that proposed method can be used as a preliminary survey to find where needs the detailed inspection.