University of Portsmouth Higher Education Corporation and ABL 1 Touch Group Limited KTP 24_25 R4

A car's bodywork is photographed and assessed by an AI system that then schedules the repair work, all within minutes. This project tackles a persistent bottleneck in the automotive repair industry: the slow, manual process of inspecting damage and coordinating workshop capacity. Currently, a technician must visually assess dents and scratches, estimate repair time, and manually slot the job into a busy schedule. This is time-consuming and prone to human error or inconsistency. The researchers are building a system that uses machine learning to analyse images of vehicle damage and computer vision to classify its severity, then automatically optimises the repair schedule based on parts availability and workshop resources. If successful, the system could cut inspection time from tens of minutes to seconds, reduce scheduling conflicts, and increase the number of repairs a workshop can handle per day. For the customer, this means faster turnaround and more accurate cost estimates. For the repair sector, it establishes a new technical benchmark for operational efficiency, allowing smaller firms to compete with larger chains through smarter automation rather than larger premises.