Abstract
Pennsylvania experienced more than 3000 pedestrian-related injuries in 2022, according to PennDOT [1], and the Governor’s Highway Safety Association estimates that Pennsylvania ranked 10th among all 50 states in 2022 for the most pedestrian fatalities [2]. This project will explore and evaluate the potential for connected autonomous vehicles (CAVs) to reduce these pedestrian-involved incidents. While many past works have explored using CAV capabilities to detect and avoid pedestrians, we will specifically focus on ensuring that these benefits are felt where and when they are most needed.
Recent studies show that pedestrian fatalities in the United States are especially common at night and on roads that do not have infrastructure designed to support pedestrians. By increasing the concentration of CAVs, which may be safer for pedestrians, on such dangerous roadways, we may be able to increase overall pedestrian safety. Many pedestrian-related incidents, for example, involve human driver distraction, and CAVs can make use of non-visual (e.g., radar) environmental data to detect pedestrians, especially at night. However, CAVs may also be more dangerous for pedestrians if their detection systems fail. Moreover, intentionally diverting CAVs to areas that are dangerous for pedestrians may have implications for safety and traffic flow through the road network as a whole. For example, proactively routing CAVs to these areas may create more traffic congestion and potentially increase accidents involving vehicles, leading human-driven vehicles to avoid this area. Indeed, CAVs will likely be deployed initially in mixed-autonomy settings with human-driven vehicles, which adds an additional layer of complexity in analyzing how pedestrians will affect safety or traffic flow.
We plan to build on our 2023-4 Safety21 project investigating CAVs’ safety effects in road networks. In particular, we will make use of our mixed autonomy simulator from the previous project, which includes models of vehicle-involved accidents but does not explicitly seek to improve pedestrian safety. Our work will comprise four parts: (i) integrating pedestrian fatality and injury statistics into our mixed autonomy simulator, (ii) developing analytical models for traffic flow and pedestrian injuries/fatalities given CAV routing, (iii) designing algorithms for CAVs to minimize pedestrian fatalities and injuries, and (iv) using the simulator and our analytical models to evaluate whether CAVs can effectively reduce pedestrian injuries and fatalities, as well as any tradeoffs with increasing traffic congestion.
[1] Pennsylvania Department of Transportation, 2022 Pennsylvania Crash Facts and Statistics. https://www.penndot.pa.gov/TravelInPA/Safety/Documents/2022_CFB_linked.pdf
[2] Governors Highway Safety Association. Pedestrian Traffic Fatalities by State: 2022 Preliminary Data (January - December). https://www.ghsa.org/sites/default/files/2023-06/GHSA%20-%20Pedestrian%20Traffic%20Fatalities%20by%20State%2C%202022%20Preliminary%20Data%20%28January-December%29.pdf
[3] E. Badger, B. Blatt and J. Katz. Why Are So Many American Pedestrians Dying at Night? The New York Times, December 11, 2023.
Description
Timeline
Strategic Description / RD&T
Section left blank until USDOT’s new priorities and RD&T strategic goals are available in Spring 2026.
Deployment Plan
We list our planned activities and deliverables for each quarter below.
Q1: Development of models for pedestrian injuries and fatalities given CAV distribution around a road network and the prevalence of CAVs and human-driven vehicles. We will use our prior work on traffic flow and mixed-autonomy settings to model the flow of CAVs and human-driven vehicles around a city’s road network, given current congestion levels and vehicle and pedestrian incidents. Our main deliverable will be new mathematical models of CAV movement and incident rates around a city.
Q2: Development of algorithms for CAVs to route themselves around a city so as to minimize pedestrian fatalities, given the models developed in Q1. Our main deliverable will be two versions of these algorithms, one that assumes CAV coordination and one that does not.
Q3: Development of a mixed-autonomy simulator that incorporates pedestrian incident data on realistic road network topologies, using our models of CAV, human driver, and human pedestrian behavior. We plan to build on the simulator we had previously developed with Mobility21’s support. We will also consult with SPC on other potential sources of data and deployment concerns that we should include in the simulator. Our main deliverable will be the simulator code and data, which we will release publicly.
Q4: Evaluation of our proposed models and algorithms in the mixed-autonomy simulator. See below for specific anticipated outcomes and outputs of this evaluation. Our main deliverable will be a quantitative analysis of the impact of CAVs on pedestrian safety. We will in particular evaluate the tradeoffs between CAVs’ improving pedestrian safety and potentially increasing traffic congestion.
Expected Outcomes/Impacts
Regulatory agencies, including our partner the City of Pittsburgh’s Department of Mobility and Infrastructure, may be able to use our results to forecast the effects of gradually increasing CAV deployment, particularly with regards to pedestrian safety. Similar to our prior "Big Idea" project with Mobility21 and current project with Safety21, on which this project builds, our work could inform the policies that agencies may wish to take in regulating CAVs (e.g., developing guidelines for how CAVs should route themselves around a city). It will further provide quantitative validation for (or evidence against) claims that CAVs can benefit traffic and traffic safety as a whole. Finally, our simulator may aid such agencies and other researchers in studying CAV and human behavior in mixed-autonomy systems. We further plan to explore collaborations with the Southwestern Pennsylvania Commission, which was a partner for our prior work, as they may also find our results to be of interest.
CAV manufacturers and service providers, like our partner the Transportation Research Center, may also be able to benefit from this work, as it will help them quantify the importance of developing CAVs that interact “well” with humans and design learning algorithms that help CAVs to do so. These new learning techniques may enhance the benefits of CAVs and increase their potential for deployment. They may also help CAV service providers earn public trust of CAVs, by demonstrating that CAVs may have benefits for pedestrian safety.
Expected Outputs
Our deliverables will be (i) new algorithms for CAVs to improve pedestrian safety by reducing injuries in fatalities at times and locations where they are more likely to occur; (ii) new models of CAVs’ effects on pedestrian injury and fatality rates in mixed-autonomy settings; (iii) quantitative estimates of how much CAVs can reduce pedestrian injuries and fatalities, given a realistic road network and CAV prevalence; (iv) quantitative estimates of any performance tradeoffs between improving pedestrian safety and worsening traffic congestion; (v) regulatory implications of these quantitative findings; and (vi) extensions of our existing mixed autonomy simulator to include better models of pedestrian behavior, injuries, and fatalities.
We will work with our deployment partner, DOMI, to ensure the usefulness of our project outputs, through regular meetings for feedback. We will also seek feedback from deployment partner, the Transportation Research Center, as to whether our CAV models are realistic. We will consider leveraging DOMI’s existing public participation processes to receive community feedback on our work. We expect that this feedback will allow us to account for metrics that are important for all communities affected by CAV deployments, helping to ensure that we address concerns associated with CAV deployments.
TRID
We have attached the results of a TRID search for “pedestrian safety autonomous vehicle road networks,” which returned 27 results. The majority (twenty-three results) focused on using CAVs’ sensing capabilities to predict pedestrian behavior or detect the presence of pedestrians. We plan to use this literature to inform our pedestrian injury and fatality rate models for vehicles operating at different levels of autonomy in a given environment (e.g., with and without daylight). These estimates can be further informed by the results from our search that examine how CAVs or automated traffic lights can optimize their interactions with pedestrians, e.g., optimizing vehicle-to-vehicle communications to improve pre-crash safety (result 23). Another work, result 2, develops models for how pedestrians interact with traffic in an intersection, and we will use their results to inform our mixed autonomy simulator. In contrast to all of these works, however, we focus on the network-wide impact of CAVs’ effects on pedestrian safety.
The remaining results of our search either focus on aiding pedestrians in safely crossing intersections (result 14), are broad surveys or overviews (two results), or focus on CAV safety, but not specifically on pedestrians (result 5, which is also our prior Safety21 project).
Individuals Involved
| Email |
Name |
Affiliation |
Role |
Position |
| cjoewong@andrew.cmu.edu |
Joe-Wong, Carlee |
ECE |
PI |
Faculty - Untenured, Tenure Track |
| oyagan@andrew.cmu.edu |
Yagan, Osman |
ECE |
Co-PI |
Faculty - Research/Systems |
Budget
Amount of UTC Funds Awarded
$90000.00
Total Project Budget (from all funding sources)
$180000.00
Documents
Match Sources
No match sources!
Partners
| Name |
Type |
| City of Pittsburgh |
Deployment Partner_ Deployment Partner_ |
| Transportation Research Center |
Deployment Partner Deployment Partner |
| Southwestern Pennsylvania Commission |
Deployment Partner_ Deployment Partner_ |
