Automated Driving Systems (ADS) for Rural America
A Ford Transit 350HD automated shuttle bus is about to embark on a two-year journey traversing a 47-mile loop of Midwestern roadways — with multiple destinations critical for equitable development of autonomous driving functions along the way.
The Automated Driving Systems (ADS) for Rural America project will collect and publish data to help train automated driving software for rural roads, all while illustrating the benefits of autonomy to populations currently underserved by public transportation options. And the impressions of those passengers before, during and after sessions of automated transport will supplement data recorded by the suite of sensors during their ride.
The National Advanced Driving Simulator (NADS) at the University of Iowa oversees the ambitious ADS for Rural America project as part of a $7 million research grant awarded by the U.S. Department of Transportation. NADS and Hexagon | AutonomouStuff collaborated to develop the Ford Transit 350HD ADS platform using the PACMod 3.0 drive-by-wire system.
"Our mission is to look at the connection between all road users and how we can make things safer," said Omar Ahmad, project manager and NADS deputy director. "When we look at automated vehicles, it's clear there's an over-emphasis on urban areas and interstates. Until now the focus has been on perfect roads in perfect weather—we will examine the challenges of rural environments, which are often imperfect."
The rural Iowa roads selected for the route through Iowa City, Kalona, Riverside and Hills represent the types of scenarios that automated vehicles will regularly encounter beyond city borders: inconsistent lane markings and surface conditions; great disparities in the speed and type of vehicles using the roadway, such as farm equipment; and inclement weather, including heavy snow that obscures paved surfaces. Outside Kalona, motorists share the road with horse-drawn carriages from a nearby Amish community.
"We didn't want to just cherry pick roads that are going to be easy," Ahmad said. "We really wanted to throw real-world USA roads at it, so we can get an honest assessment... (Automated vehicles) should work just as well on these types of roadways as in cities and on interstates."
The need for safer transportation on such roadways is great. While only 19 percent of Americans live in rural areas, nearly 50 percent of fatal traffic crashes occur on rural roads. And aging populations, including residents who have disabilities that prevent them from driving, lack consistent access to public transportation in most rural areas.
The ADS for Rural America project aims to show how automated vehicles can help fill that need while collecting valuable data about passenger perception. Beginning this summer, residents in the region can volunteer online at adsforruralamerica.uiowa.edu/participate to participate as passengers. They will be surveyed about their experiences aboard the automated shuttle bus (always with a safety driver and co-pilot onboard), while having biometric data recorded in sync with camera footage and raw data from LiDAR and RADAR sensors.
"We're very interested in their trust and acceptance before, during and after being in a vehicle like this," Ahmad said. "There's going to be a range of opinions and pre-conceived notions of what these vehicles are and what they mean — and we need to understand that better."
The automated shuttle bus will hit the road over the summer of 2021, with the first sets of data to be posted soon afterward. Data will include video footage, questionnaire data, physiological data on stress/anxiety, and automation performance data. And it's not too late for developers to make data collection requests by reaching out through the project website.
"Our goal is to share the data as we collect it—critical for researchers around the world so they can include the uniqueness of rural driving in their models," Ahmad said.