Safe-D: Safety through Disruption

Upcoming Webinars

If you would like to be notified of future Safe-D webinars, please fill out this form.

Title/Project/DateSpeaker(s)Webinar Overview
Title: Developing Artificial Intelligence Driven Safe Navigation Tool

Project: Safe-D 06-002

Date: December 5, 2023, 14:00 ET

Zoom Link: Register via Zoom

Subasish Das
Subasish Das, Ph.D.,
Texas A&M Transportation Institute
Popular navigation applications such as Google Maps and Apple Maps provide distance-based or travel time-based alternative routes with no real-time risk scoring. There is a need for a real-time navigation system that can provide the data-driven decision on the safest path or route. By leveraging data from a diverse range of historical and real-time sources, this study successfully developed a user interface for a navigation tool or application that offers informed and data-driven decisions regarding the safest navigation options. The interface considers multiple scoring factors, including safety, distance, travel time, and an overall scoring metric. This study made a distinctive and valuable contribution by designing and implementing a robust safe navigation tool driven by artificial intelligence. Unlike existing navigation tools that offer multiple uninformed route options, this tool provides users with an informed decision on the safest route. By leveraging advanced AI algorithms and integrating various data sources, this navigation tool enhances the accuracy and reliability of route selection, thereby improving overall road safety and ensuring users can make informed decisions for their journeys.
Title: Measuring the Safety of ADS: How Safe is Safe Enough?

Project: Safe-D 06-014

Date: January 25, 2024, 14:30 ET

Zoom Link: Register via Zoom

Eileen Herbers
Eileen Herbers,
Virginia Tech Transportation Institute
A common question determining the eventual deployment of automated driving systems is “how safe is safe enough?”. This research uses naturalistic driving data to determine how to measure the potential safety benefit of automated vehicle technologies and automated driving systems (ADS), and where current technology practices may not deliver on projected safety promises. ADS are being developed faster than any point in history. There is a need to have an independent system to measure the safety of ADS across technologies and corporations. There are a variety of efforts around the world trying to estimate the impact of these systems on safety both prior to and after implementation. A missing piece that could allow for more cohesion and safer implementation is the knowledge of what type of data is needed for the refinement and further development of these systems, as well as which scenarios may not be able to be addressed by the currently implemented technology. The purpose of this project is to use naturalistic driving data to inform scenario selection that will be used to measure how ADS will perform in these scenarios.

Specifically, events are chosen partly from the results of a previous project in which naturalistic crash and near-crash scenarios were modeled to determine how the inclusion of line-of-sight and connected vehicle technologies could have impacted the event. Safety surrogate measures are calculated to determine the impact of changing event parameters and to estimate the potential crash severity of different scenarios. Other epochs are chosen based on situations where certain perception systems may have difficulty in correctly identifying the location and classification of certain objects. Overall, this research is meant to create and analyze some scenarios in which the technology being developed in ADS may not provide the predicted advantage of reducing or mitigating safety-critical events.

Title: A Conceptual Model of the ADAS Ecosystem: Gaps in the Literature and Research Needs

Project: Safe-D 06-003

Date: February 15, 2023, 14:30 ET

Zoom Link: Register via Zoom

Tara Goddard
Tara Goddard, Ph.D.,
Texas A&M Transportation Institute
Rebecca Sanders
Rebecca Sanders, Ph.D.,
Texas A&M Transportation Institute
While simple alerts and functions to assist automobile drivers and increase convenience have existed for decades, modern advanced driver assistance systems (ADAS) are increasingly complex and vary widely by manufacturer and even specific vehicle trim level. Additionally, these technologies have proliferated rapidly through the current vehicle fleet faster than behavioral research can keep up. Much existing research has focused on drivers’ use of technologies during the driving task, with its direct relationship to safety. Also of interest to safety professionals and consumers, however, should be factors related to selling and buying, including marketing, naming, availability, dealer and consumer knowledge, vehicle handoff at purchase, and challenges posed by the increase in online vehicle marketplaces with minimal interaction between seller and consumer. In this webinar, we will give a brief overview of the existing research on several of these factors, identify major gaps, and introduce a conceptual model to make the case that the entire ADAS ecosystem needs more research to ensure that these technologies benefit individual consumers and the larger transportation system. While some aspects of this model could be applied broadly to any new vehicle design or technology, we focus on ADAS because they are broadly available technologies and touted as key to national safety goals, yet are currently optional (pre and post purchase) and vary widely regarding marketing strategies, consumer and seller knowledge and training, and potential safety improvements.