News | PSR Researchers Estimate the Environmental Impact of Autonomous Emergency Braking

Stop the Video



by Georgie Suico

In 2019, almost 7 million traffic crashes took place in the United States, contributing to the majority of the country’s road congestion. These crashes and the resulting congestion incur environmental costs, with drivers wasting fuel by taking longer routes or sitting in traffic. Automatic/Autonomous Emergency Braking (AEB), a safety feature within advanced driving assistance systems (ADAS), was developed as a means of preventing accidents. This technology allows a vehicle to detect emergencies and initiate the vehicle’s brakes to avoid collision. Although AEB’s main goal is to prevent both the loss of life and property damage, the consequential environmental impact due to congestion mitigation has been severely understudied. In a recent PSR report published last June, Estimating the Impacts of Automatic Emergency Braking (AEB) Technology on Traffic Energy and Emissions, researchers Guoyuan Wu, Associate Researcher at the University of California, Riverside; Matthew Barth, Director of Bourns College of Engineering – Center for Environmental Research & Technology (CE-CERT) at the University of California, Riverside; Xishun Liao, Research Assistant at the University of California, Riverside; and Lan Yang, Visiting Scholar from Chang’an University investigated the traffic-level impacts of AEB technology. Identifying a critical gap in existing literature, the research team sought to study AEB and its overall effect on environmental sustainability (including energy and tailpipe emissions) and traffic congestion, rather than its safety benefits to individual vehicles.

The team conducted case studies for both the City of Riverside, CA and the City of Las Vegas, NV. An integrated database was constructed for each area including the following data: real-world traffic measurements from inductive loop detectors (e.g., the Caltrans Performance Measurement System) or probe vehicles; traffic accident records (such as the Highway Safety Information System); physical roadway characteristics; and weather information. Using this database, the team developed a machine learning model to predict the evolution of traffic dynamics if the crashes did not occur and estimated the impact on traffic due to potential avoidance of the accident. The researchers then used the U.S. Environmental Protection Agency’s Motor Vehicular Emission Simulator (MOVES) to estimate the reduction, as a result of AEB, in air emissions, CO2 emissions, and energy and fuel consumption. Case study results indicated that AEB reduced tailpipe pollutant emissions by up to 22.5% and energy consumption by up to 34.6%. The table below gives values and percent change for criteria pollutants, CO2, energy and fuel consumption.

In the future, the team plans to improve the evaluation method for AEB impact by including other factors such as road grade, vehicle mix, and meteorological conditions, which were not analyzed in this study. The conclusions reached by Wu’s team also suggest some policy implications. For instance, if AEB contributes substantial benefits for sustainability, traffic-prevention, and safety for individual passengers, should more measures be taken to encourage AEB’s integration into a wider selection of vehicle models? As transportation research continues to focus on increasing safety and efficiency as well as reducing carbon emissions, AEB will play a significant role as it becomes more widely adopted.