Data-driven framework for pothole repair automation using unmanned ground vehicle fleets

Abstract

Traditional pavement repair techniques are time-consuming, labour-intensive, prone to errors, and expose manpower to high-risk road traffic conditions. This paper proposes a data-driven solution for planning and automating the repair process for road potholes using a fleet of unmanned ground vehicles (UGVs). The project encompasses data mining, developing software tailored for fleet management, and enhanced fault tolerance. Additionally, it incorporates the integration of digital twins for advanced simulation purposes. The methodologies involve cross-industry standard processes for data mining (CRISP-DM) and preparation combined with rapid application development (RAD). To optimise repair schedules, the system takes parameters like fleet size, payload capacity, and material requirements based on pothole dimensions. This data-driven project concludes from simulations that a neighbourhood can be patched about 40 % faster and optimised to achieve a 12.5 % reduction in robot inter-travel time using three UGVs per defined residential area of 100,000 m² instead of two UGVs in the fleet.