BP trial proves accuracy of AI-based range prediction app
A trial among BP employees has verified the accuracy of an AI-based range prediction app compared to official manufacturer systems, showing how it could help aid EV adoption.
Launched two years ago by software company Spark EV Technology, the plug and play solution and accompanying smartphone app use Artificial Intelligence software algorithms to predict journeys for electric vehicles based on live data, previous trips and chargepoint locations.
Under partnership with BP, the solution has now been trialled by BP employees in a move that will aid development of future versions of the software.
The project saw BP employees based at five locations drive 10,000km (around 6,200 miles) in two types of EVs equipped with Spark’s journey prediction solution and supplied by Zipcar and Avis Budget Group.
Drivers entered details of planned journeys into Spark’s smartphone application to record data and make comparisons with the onboard range display. They then received personalised advice on whether they could complete their journey – based on live data, driving style, urban/country routes, previous trips and charge point locations.
The trial showed how Spark EV’s Technology brought much higher levels of accuracy on range compared to manufacturer data. Based on the manufacturer information, the trial found that one car could have completed an extra 45 miles than its displayed range during a single journey while another journey required an extra 21 miles more range than the car had predicted. Yet for the same journeys, the Spark system predicted the range to an accuracy of just 3.8 miles and 0.4 miles respectively.
And, with Spark’s AI algorithms learning with every journey, this continually improves the accuracy of personalised journey predictions.
“Our trial with Spark EV helped to increase our understanding of how technology could help reduce consumer range anxiety, especially for new EV drivers,” said Sophia Nadur, innovation director, BP. “We now look forward to working together to explore further potential applications into future software iterations.”
Justin Ott, CEO, Spark Technology, added: “The success of this initial project has opened up major new opportunities for Spark within the automotive sector as we launch our new fundraising round. We look forward to working together further in the future.”