BMW i Ventures makes strategic investment in smartphone driving analytics company Zendrive

25 November 2014

The BMW Group’s venture capital company, BMW i Ventures, has made an investment in the startup Zendrive, a company that uses data and analytics gathered from smartphones rather than OBD to improve driving through driving analytics. Related BMW mobility services investments currently include JustPark, Chargepoint, Life360, Chargemaster, and MyCityWay. The Zendrive investment is the first in a series of investment announcements that will be made in the months ahead, said Ulrich Quay, Managing Director of BMW i Ventures, LLC.

Zendrive uses the sensors on a smartphone to measure a driver’s behaviors; Zendrive’s Driver-Centric Analytics process the data from the phone’s sensors into a Zendrive score that factors in cell phone use, speed, swerves, hard stops, fast accelerations, fatigue, as well as weather, trip duration, time of day, and more.

<!——>

Zendrive offers a great addition to our portfolio and advances the BMW Group vision of convenient, safe and efficient mobility. BMW and Zendrive will explore ways to co-operate on innovative, car-related services in order to make the in-car mobility experience even smoother by optimizing commuting and driving patterns for a safer, more convenient ride.

In a whitepaper (Meng et al.) published on the company’s site, three of the Zendrive team (from the University of Illinois) report that smartphones can attain speed estimations that correlate 98% to OBD without energy constraints, and around 94.6% to OBD when GPS is completely turned off.

The results are reasonably robust to various scenarios, such as in highways and city streets, weather and traffic conditions, and different phone placements. The Zendrive team sugests that further improvements are possible through more sophisticated machine learning and signal processing on the sensor data.

With the personal transportation ecosystem poised for disruption, its unclear if OBDs or smartphones will serve as the platform for technological innovation. This paper is an attempt to compare and contrast their capabilities and how they translate to the end goal of understanding driving analytics.

We observe that while smartphone sensors are noisy on one hand, the variety of sensors available to them, in conjunction with their access to the Internet, makes it an extremely agile and powerful platform. Even though no single smartphone sensor can directly estimate speed like the OBD, they can together orchestrate information from various sources to achieve a 96% similarity to OBD. This orchestration involves understanding when a car stops and turns from accelerometers and compasses, utilizing crowd-sourced data from the roads, leveraging the driver’s historical patterns, etc.

Further research in sensor fusion and machine learning will enable deeper insights into driving behavior, including aggressive braking and acceleration, accidents, dozing off, etc. Finally, it is possible to execute such data-driven analytics on a low energy budget, implying that a smartphone-based system is amenable to public adoption. In light of these advantages, and more that are emerging in the field of mobile sensing, the smartphone platform is likely to become a superset of OBDs in a vast majority of driving scenarios.

Founded in 2013 and based in San Francisco, CA, Zendrive is striving to make driving better, safer, and more efficient for everyone through improved data and analytics. Zendrive’s customers include rideshare companies, valet parking and other service providers. Investors include First Round Capital, BMW i Ventures, and Bill Ford’s Fontinalis Partners, as well as founders of Yahoo, PayPal, and GenRe re-insurance.