Safe and Sustainable Fleet Management with Data Analytics and Reinforcement Training

Abstract

The University of Virginia's Facilities Management (FM) Fleet consists of around 260 total vehicles and is committed to safe and sustainable driving. The fleet vehicles contain telematic tracking systems which provide feedback on a multitude of driving behavioral measures, including speeding, harsh braking, hard acceleration, seat belt usage, harsh cornering, and idling time. In a previous study, data collected on these measures was used to develop relevant educational materials on mindful driving. This paper aims to further improve safe and eco-friendly FM driving behaviors by analyzing if reinforcement training, additional scorecards and manager conversations, proved to be effective when given proactively or reactively to increased violations of driving behavioral measures. This paper outlines the process we used in determining when and how to administer the two different training programs and which vehicle shops to involve. One group of shops received in-depth training before any notable violations were detected, which was deemed proactive training. A separate shop received the reactive training after any significant increase in vehicle incidents was detected. These reinforcement training programs were largely based on the professional FM education modules and provided conversation templates for managers to use in order to re-educate their shop's respective drivers. The research showed that reactive reinforcement training was statistically significant for speeding while proactive reinforcement training was not statistically significant; however, further expansion upon both trainings may still be warranted.