SBIR Phase II: Data Analytics and Physics-Based Insights into Vehicle Mobility Patterns

The broader impact/commercial potential of this Small Business Innovation Research (SBIR) project is to provide new insight to consumers on their vehicle use, to inform environmental and economic impact. Unfortunately, typical car buyers currently do not understand their mobility patterns, and in particular how electric vehicle (EV) fuel costs and range viability will impact their day-to-day lives. Thus, prospective car buyers may not appreciate the potential financial and practical savings. This SBIR Phase II project proposes to support the development of data collection, processing, and analytical methods to measure an individual's (or fleet) driving tendencies to predict the value and viability of EV use. This can potentially save billions of gallons of avoided petroleum use as well as hundreds of billions in associated costs, and dramatically reduced emissions. The proposed project advances data science, machine learning, and convex optimization techniques to estimate vehicle performance. This project has three stages: (1) develop mathematical and physics-based algorithms for predicting the energy or charge requirements and range viability for any electric vehicle on any trip, including uncertainty bounds on the calculated results; (2) integrate the trip energy calculations to develop algorithms that predict and optimize EV charging deployments; (3) develop algorithms for use at scale. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.