Andreas Lamprecht

The Car as an Ambient Sensing Platform [Point of View]

In recent years, cars have evolved from purely mechanical to veritable cyberphysical systems that generate large amounts of real-time data. These data are instrumental to the proper working of the vehicle itself, but make them amenable to a multitude of other uses. For instance, GPS information has recently been used for a large number of mobility studies in the academic community [1] , [5] , as well as to feed traffic apps such as Google Traffic and Waze. This use of vehicle data is already having a profound impact in science, industry, economy, and society at large. Now, imagine that instead of accessing one single source of vehicle-generated data (GPS), one can access the entire wealth of data exchanged on the controller area network (CAN) bus in near real timeamounting to over 4000 signals sampled at high frequency, corresponding to a few gigabytes of data per hour. What would be the implications, opportunities, and challenges sparked by this transition?

Driver identification using automobile sensor data from a single turn

As automotive electronics continue to advance, cars are becoming more and more reliant on sensors to perform everyday driving operations. These sensors are omnipresent and help the car navigate, reduce accidents, and provide comfortable rides. However, they can also be used to learn about the drivers themselves. In this paper, we propose a method to predict, from sensor data collected at a single turn, the identity of a driver out of a given set of individuals. We cast the problem in terms of time series classification, where our dataset contains sensor readings at one turn, repeated several times by multiple drivers. We build a classifier to find unique patterns in each individuals driving style, which are visible in the data even on such a short road segment. To test our approach, we analyze a new dataset collected by AUDI AG and Audi Electronics Venture, where a fleet of test vehicles was equipped with automotive data loggers storing all sensor readings on real roads. We show that turns are particularly well-suited for detecting variations across drivers, especially when compared to straightaways. We then focus on the 12 most frequently made turns in the dataset, which include rural, urban, highway on-ramps, and more, obtaining accurate identification results and learning useful insights about driver behavior in a variety of settings.