The Advanced Vehicle Technology (AVT) Consortium was launched in September 2015 with the goal of achieving a data-driven understanding of how drivers engage with and leverage vehicle automation, driver assistance technologies, and the range of in-vehicle and portable technologies for connectivity and infotainment appearing in modern vehicles.
Using advanced computer-vision software and big data analytics, researchers are gathering data to quantify drivers' actions, such as how they respond to various driving situations and perform other actions like eating or having conversations behind the wheel. The research is studying the moments when control transfers from the driver to the car and back again, as well as how drivers respond to alarms (lane keeping, forward collision, proximity detectors, etc.) and interact with assistive and safety technologies (e.g., adaptive cruise control, semi-autonomous parking assistance, vehicle infotainment and communications systems, smartphones and more). The effort aims to develop human-centric insights that drive the safety efficacy of automated vehicle technology development and advances the consumer's understanding of appropriate technology usage.
Who is Involved?
As an academic industry partnership, the AVT Consortium brings together key stakeholders in the automotive ecosystem in a unique collaborative effort at Massachusetts Institute of Technology (MIT).
The founding members of the AVT Consortium are the MIT AgeLab, Touchstone Evaluations, and Agero.
Consortium membership also includes automakers, insurance companies, tier-1 suppliers, and research organizations. Current members in addition to the three founding members of the consortium are:
|Aptiv||Jaguar Land Rover|
|Audi / AID||Liberty Mutual Insurance|
|TravelCenters of America|
The Insurance Institute for
Initial Data Collection and Timeline
Data collection began in January 2016 and is expected to continue for several years, gathering data and insights on the ongoing innovations in automotive technology and changing consumer behaviors related to portable technologies brought into the vehicle. As of the February 25, 2019, the consortium has gathered data across more than 15,610 participant days, 122 drivers, 29 vehicles, 511,638 miles of travel, and 7.11 billion video frames. The study is currently actively collecting data in instrumented Tesla models S and X vehicles, Cadillac CT6 vehicles equipped with Super Cruise, Volvo S90 vehicles equipped with Pilot Assist technology, and Range Rover Evoques with a range of advanced driver assistance features. The effort plans to add new vehicles of interest as they are introduced into the marketplace. Recorded data streams include IMU, GPS, CAN messages, and high-deﬁnition color video of the driver's face, body positioning, the driver cabin, the forward roadway, and the instrument cluster (on select vehicles). Questionnaire and interview data is collected to provide qualitative insight in additional to the vast amount of objective data obtained.
Among other objectives already mentioned, the MIT AgeLab is leveraging the multiple streams of high-definition video obtained as part of this large-scale real-world driving data collection to fuel the development of deep learning based internal and external perception systems. This is taking place within the broader effort of gaining a holistic understanding of how human beings interact with vehicle automation technology by integrating video data with vehicle state data, driver characteristics, mental models, and self-reported experiences with technology and other factors related to automation adoption. In addition to analytic efforts being carried out collaboratively within the consortium, individual members are utilizing portions of the dataset to delve deeper into questions of specific interest to their organizations, both with and without direct involvement of the MIT AgeLab. At the most fundamental level, these efforts aim to identify how technology and other factors related to automation adoption and use can be improved in ways that save lives.
Key Methodological Details
Fridman, L., Brown, D.E., Glazer, M., Angell, W., Dodd, S., Jenik, B., Terwilliger, J., Kindelsberger, J., Ding, L., Seaman, S., Abraham, H., Mehler, A., Sipperley, S., Pettinato, A., Seppelt, B., Angell, L., Mehler, B., & Reimer, B. (2017). MIT autonomous vehicle technology study: large-scale deep learning based analysis of driver behavior and interaction with automation.
Initial AVT Publications
Abraham, H., Lee, C., Brady, S., Fitzgerald, C., Mehler, B., Reimer, B. & Coughlin, J.F. (2017). Autonomous vehicles and alternatives to driving: trust, preferences, and effects of age. Proceedings of The Transportation Research Board 96th Annual Meeting, Washington, D.C.
Abraham, H., McAnulty, H., Mehler, B., & Reimer, B. (2017). Case study of today's automotive dealerships: introduction and delivery of advanced driver assistance systems. Transportation Research Record, No. 2660, pp. 7-14.
Abraham, H., Reimer, B., & Mehler, B. (2017). Advanced driver assistance systems (ADAS): a consideration of driver perceptions on training, usage & implementation. Proceedings of the Human Factors and Ergonomics Society Annual Meeting, 61(1), pp. 1954-1958. Austin, TX.
Abraham, H., Seppelt, B., Mehler, B., & Reimer, B. (2017, September). What's in a name: vehicle technology branding & consumer expectations for automation. Proceedings of the 9th International Conference on Automotive User Interfaces and Interactive Vehicular Applications (AutoUI), Oldenburg, Germany, September 24-27.
Seppelt, B., Reimer, B., Angell, L., Seaman, S. (2017). Considering the human across levels of automation: implications for reliance. Proceedings of the 9th International Driving Symposium on Human Factors in Driver Assessment, Training and Vehicle Design. Manchester Village, VT.