Browsing by Author "Dobrovolny, Chiara Silvestri"

Now showing 1 - 4 of 4
  • Thumbnail Image
    Crashworthiness Compatibility Investigation of Autonomous Vehicles with Current Passenger Vehicles
    Dobrovolny, Chiara Silvestri; Stoeltje, Gretchen; Zalani, Aniruddha (SAFE-D: Safety Through Disruption National University Transportation Center, 2021-11)
    Automated Vehicles have been one of the most sought-after concepts to make transportation more effective and safer. No-occupant vehicles with automated driving systems (ADS) make up one such class of vehicles. These are primarily intended for goods transportation services. This vehicle class presents a body structure different than that of a passenger vehicle. Yet, these no-occupant ADS-equipped vehicles are sharing the roads and could potentially be involved in crashes with passenger vehicles. Occupant safety may be compromised if vehicles are not compatible from a crashworthiness perspective. ADS-equipped vehicles should consider appropriate vehicle crashworthiness compatibility given the potential for interactions with vulnerable road users and other vehicle types. Investigation of the level of ADS-equipped vehicle crashworthiness compatibility with human-driven vehicles can lead to more appropriate vehicle designs, as well as more suitable and better passive protection systems for occupants in such crash scenarios. This research project considers finite element crash computer simulation investigation between ADS-equipped and passenger vehicles with the intent to provide a better understanding of the differences in crashworthy behavior of ADS-equipped vehicles.
  • Thumbnail Image
    Detecting Pavement Distresses Using Crowdsourced Dashcam Camera Images
    Dadashova, Bahar; Dobrovolny, Chiara Silvestri; Tabesh, Mahmood (SAFE-D: Safety Through Disruption National University Transportation Center, 2021-05)
    Pavements play a vital role in the transportation infrastructure in the United States. Damage to public road transportation infrastructure causes roadways to fail to perform as intended and increases crash risks. Road damage must be detected quickly and accurately in order to maintain roads and effectively allocate repair money. In this study, four deep-learning object detection models were used for detecting five types of pavement damages using Nexar Dashcam images. The single-shot multi-box detector (SSD) and faster region-based convolutional neural networks (Faster R-CNN) object detection models using MobileNet and Inception techniques were applied to the selected and processed images. An attempt was made to detect alligator cracking, longitudinal cracking,transverse cracking, and patching on the roadway surface using the developed model. A total number of 6,326 images with a total number of 8,970 damage instances were selected from the provided data. Faster R-CNN models showed higher recall and precision compared to the SSD models. Faster R-CNN Inception Resnet showed the highest average precision of 56%, followed by Faster R-CNN Inception with an average precision of 50%. Recall values showed almost the same trend as precision. Faster R-CNN showed the highest average recall of 43%. The results showed that Type-I and Type-II damages were detected with the highest recall and precision compared to other damages. Type-I damage was detected with an average precision of 81% and recall of 70 % in all of the models.
  • Thumbnail Image
    Implications of Truck Platoons for Roadside Hardware and Vehicle Safety
    Dobrovolny, Chiara Silvestri; Untaroiu, Costin D.; Sharma, Roshan; Jin, Hanxiang; Meng, Yunzhu (SAFE-D: Safety Through Disruption National University Transportation Center, 2019-10)
    Platooning is an extension of cooperative adaptive cruise control and forward collision avoidance technology, which provides automated lateral and longitudinal vehicle control to maintain short following distances and tight formation. The capacity and adequacy of existing roadside safety hardware deployed at strategic locations may not be sufficient to resist potential impact from an errant fleet of multiple trucks platooning at high speed. It is unknown how these impacting trucks might interact with roadside safety barriers after leaving their platoon and what the occupant risks associated with such impacts may be. This research identifies and prioritizes the critical Manual for Assessing Safety Hardware TL5 roadside safety devices for truck platooning impact assessment in order to understand the associated roadside and occupant risks and hazards. Finite element models of the trucks and roadside safety devices are examined using multiple computer simulations for various scenarios. Occupants injury risks during truck collision simulations are assessed using dummy and human finite element models. The results and implications can provide a better understanding of whether any roadside safety device improvements and/or platooning constraint modifications will be necessary before implementing truck platooning.
  • Thumbnail Image
    Motorcycle Crash Data Analysis to Support Development of a Retrofit Concrete Barrier System for Freeway Ramps
    Wilson, Jonathan; Sulaica, Heather; Dobrovolny, Chiara Silvestri; Perez, Marcie (SAFE-D: Safety Through Disruption National University Transportation Center, 2019-07)
    This project was intended to review the most relevant national and international studies, as well as protocols and standards that were developed to support motorcycle safety on roadways. In addition, crash data analysis was conducted to identify relevant factors involved with motorcycle accidents where the bike has impacted roadside safety barriers on flyovers/connectors or on curves. This crash data review was developed in support of an existing research project sponsored by the Texas Department of Transportation, which aims at identifying and testing retrofit options for existing concrete barriers to contain errant motorcycle occupants during an impact event.