VTechWorks staff will be away for the winter holidays starting Tuesday, December 24, 2024, through Wednesday, January 1, 2025, and will not be replying to requests during this time. Thank you for your patience, and happy holidays!

Browsing by Author "Miller, Marty"

Now showing 1 - 9 of 9
  • Thumbnail Image
    Assessing Alternate Approaches for Conveying Automated Vehicle ‘Intentions’
    Basantis, Alexis; Miller, Marty; Doerzaph, Zachary R.; Neurauter, Luke (SAFE-D: Safety Through Disruption National University Transportation Center, 2020-05)
    One of the biggest highly automated vehicle (HAV) market barriers may be a lack of user trust in the automated driving system itself. Research has shown that this lack of faith in the system primarily stems from a lack of system transparency while the vehicle is in motion—users are not informed how the car will react in an upcoming scenario—and not having an effective way to control the vehicle in the event of a system failure. This problem is particularly prevalent in public transit or ridesharing applications, where HAVs are expected to first appear and where the user has less training on and control over the vehicle. To improve user trust and perceptions of comfort and safety, this study evaluated human-machine interface (HMI) systems, focused on visual and auditory displays, to better relay the perceived driving environment and the automated vehicle “intentions” to the user. These HMI systems were then implemented into a HAV developed at the Virginia Tech Transportation Institute and tested with volunteer participants on the Smart Roads.
  • Thumbnail Image
    Click: Rideshare Naturalistic Driving Study (NDS): Seat Belt Use and Misuse
    Miller, Marty; Neurauter, Luke; Radlbeck, Joshua; McLaine, Joe (National Surface Transportation Safety Center for Excellence, 2024-06-14)
    This report investigates rear passenger seat belt use and misuse within the rideshare environment. This research employed a naturalistic driving study (NDS) approach by instrumenting rideshare vehicles with video recording equipment, yielding insights into seat belt usage patterns. Findings reveal that more than 64% of rideshare passengers did not attempt to use their seat belt, while only 25% of passengers were observed to consistently use their seat belt correctly. Although men and women exhibited similar seat belt usage rates, women were less likely to wear their seat belt correctly. Age and estimated body mass index (BMI) also appeared to influence observed seat belt usage. Children and adult seniors demonstrated the highest ideal usage rates. Passengers with higher BMI demonstrated lower seat belt usage on average. Seating position appeared to impact seat belt usage as well. Passengers in the third (furthest) row demonstrated lower overall seat belt usage compared to those seated in the second row. Notably, across the trips recorded, children and adolescents made up only a very small percentage of the overall passenger population (< 10%) within this rideshare environment. This study underscores the need for interventions to promote seat belt use in rideshare vehicles, potentially leveraging in-vehicle reminders. Addressing these challenges is crucial for enhancing occupant safety and mitigating injury risks in the rideshare context.
  • Thumbnail Image
    A Data Driven Approach to the Development and Evaluation of Acoustic Electric Vehicle Alerting Systems for Vision Impaired Pedestrians
    Roan, Michael J.; Beard, Michael; Neurauter, Luke; Miller, Marty (Safe-D National UTC, 2023-02)
    The number of electric vehicles on the road increases exponentially every year. Due to the quieter nature of these vehicles when operating at low speeds, there is significant concern that pedestrians and bicyclists will be at increased risk of vehicle collisions. This research explores the detectability of six electric vehicle acoustic additive sounds produced by two sound dispersion techniques: (1) using the factory approach versus (2) an exciter transducer-based system. Detectability was initially measured using on-road participant tests and was then replicated in a high-fidelity immersive reality lab. Results were analyzed through both mean detection distances and pedestrian probability of detection. This research aims to verify the lab environment in order to allow for a broader range of potential test scenarios, more repeatable tests, and faster test sessions. Along with pedestrian drive-by tests, supplemental experiments were conducted to evaluate stationary vehicle acoustics, 10 and 20 km/h drive by acoustics, and interior acoustics of each additive sound.
  • Thumbnail Image
    Exploratory Development of Algorithms for Determining Driver Attention Status
    Herbers, Eileen; Miller, Marty; Neurauter, Luke; Walters, Jacob; Glaser, Daniel (SAGE, 2023-09)
    Objective: Varying driver distraction algorithms were developed using vehicle kinematics and driver gaze data obtained from a camera-based driver monitoring system (DMS). Background: Distracted driving characteristics can be difficult to accurately detect due to wide variation in driver behavior across driving environments. The growing availability of information about drivers and their involvement in the driving task increases the opportunity for accurately recognizing attention state. Method: A baseline for driver distraction levels was developed using a video feed of 24 separate drivers in varying naturalistic driving conditions. This initial assessment was used to develop four buffer-based algorithms that aimed to determine a driver's real-time attentiveness, via a variety of metrics and combinations thereof. Results: Of those tested, the optimal algorithm included ungrouped glance locations and speed. Notably, as an algorithm's performance of detecting very distracted drivers improved, its accuracy for correctly identifying attentive drivers decreased. Conclusion: At a minimum, drivers' gaze position and vehicle speed should be included when designing driver distraction algorithms to delineate between glance patterns observed at high and low speeds. Distraction algorithms should be designed with an understanding of their limitations, including instances in which they may fail to detect distracted drivers, or falsely notify attentive drivers. Application: This research adds to the body of knowledge related to driver distraction and contributes to available methods to potentially address and reduce occurrences. Machine learning algorithms can build on the data elements discussed to increase distraction detection accuracy using robust artificial intelligence.
  • Thumbnail Image
    Improving Methods to Measure Attentiveness through Driver Monitoring
    Miller, Marty; Herbers, Eileen; Walters, Jacob; Neurauter, Luke (SAFE-D: Safety Through Disruption National University Transportation Center, 2022-07)
    Driver inattention poses a significant problem on today’s roadways, increasing risk for all road users. This report details our efforts in developing algorithms to detect driver inattention. A benchmark dataset was developed based on video review of driving events. Buffer-based algorithms were developed and compared using this benchmark dataset. The benchmark events were also used as a training dataset for machine learning models. Driver glance locations were important for determining driver attentiveness. In addition, vehicle speed was important for understanding the driving context, which was found to have a large impact on driver behavior.
  • Thumbnail Image
    Investigating and Developing Methods for Traditional Participant-based Data Collection with Remote Experimenters
    Miller, Marty (2023-11-09)
    This project investigated and developed methods and technologies to allow experimenters to conduct and monitor data collection from a remote location. The technologies developed consist of a desktop application that allows researchers to view the vehicle cabin and various vehicle parameters (like speed, acceleration, etc.) in real time. Physically removing researchers from the vehicle during experiments can increase realism and offer naturalistic observations in traditional, experimenter-conducted studies. The remote experimentation methods and technologies developed can be particularly helpful for studying automated driving by creating a more natural environment while still maintaining oversight and control of the experiment.
  • Thumbnail Image
    Private 5G Technology and Implementation Testing
    Vilela, Jean Paul Talledo; Mollenhauer, Michael A.; White, Elizabeth E.; Miller, Marty (Safe-D National UTC, 2023-03)
    NEC developed a Video Analytics implementation for traffic intersections using 5G technology. This implementation included both hardware infrastructure and software applications supporting 5G communications, which allows low latency and secure communications. The Virginia Tech Transportation Institute (VTTI) worked with NEC to facilitate the usage of a 3,400- to 3,500-MHz program experimental license band without SAS integration to successfully implement a private 5G deployment at the VTTI Smart Road intersection and data center. Specific use cases were developed to provide alerting mechanisms to both pedestrians and vehicles using cellular vehicle-to-everything/PC5 technology when approaching a traffic intersection and a dangerous situation is detected.
  • Thumbnail Image
    Probability of detection of electric vehicles with and without added warning sounds
    Roan, Michael J.; Neurauter, Luke; Song, Miao; Miller, Marty (Acoustic Society of America, 2021-01-26)
    Detection performance as a function of distance was measured for 16 subjects who pressed a button upon aurally detecting the approach of an electric vehicle. The vehicle was equipped with loudspeakers that broadcast one of four additive warning sounds. Other test conditions included two vehicle approach speeds [10 and 20 km/h (kph)] and two background noise conditions (55 and 60 dBA). All of the test warning sounds were designed to be compliant with FMVSS 141 proposed regulations in regard to the overall sound pressure levels around the vehicle and in 1/3 octave band levels. Previous work has provided detection results as average vehicle detection distance. This work provides the results as probability of detection (Pd) as a function of distance. The curves provide insight into the false alarm rate when the vehicle is far away from the listeners as well and the Pd at the mean detection distance. Results suggest that, although the test sounds provide an average detection distance that exceeds the National Highway Traffic Safety Administration minimum at the two test speeds, Pd is not always 100% at those distances, particularly at the 10 kph. At the higher speed of 20 kph, the tire-road interaction noise becomes dominant, and the detection range is greatly extended.
  • Thumbnail Image
    Quiet Car Detectability: Impact of Artificial Noise on Ability of Pedestrians to Safely Detect Approaching Electric Vehicles
    Neurauter, Luke; Roan, Michael J.; Song, Miao; Miller, Marty; Glenn, Eric; Walters, Jacob (National Surface Transportation Safety Center for Excellence, 2020-04-10)
    Many auto manufacturers are now producing hybrid and electric vehicles with an additive noise component to signal vehicle presence in the same way that internal combustion engine vehicles signal their presence through engine noise. The Virginia Tech Transportation Institute conducted an evaluation of quiet car detectability as part of a GM-funded project in 2015–2016. The internal combustion engine benchmark significantly outperformed the other three vehicles under a 10-km/h steady approach, but these differences largely disappeared at 20 km/h due to increased tire and road noise. Trends of improved detectability offered by the additive noise signals were observed but did not demonstrate a significant advantage over an electric vehicle with no additional noise component. Since that original project, NHTSA has released their final version of Federal Motor Vehicle Safety Standard (FMVSS) 141, outlining “Minimum Sound Requirements for Hybrid and Electric Vehicles.” This project aimed to demonstrate differences in detectability by replicating the previous study but with newer FMVSS 141-compliant sounds. The proposed additive sounds examined drastically improved detectability compared to the production variants included in the first round of testing. At 10 km/h, the additive sound conditions outperformed the no-sound condition by magnitudes ranging from 3.4 to 4.6, each eliciting mean detection distances well above the NHTSA minimum detection criteria. At 20 km/h, detectability also improved dramatically over the earlier production variants, achieving a similar magnitude advantage over no-sound as observed at 10 km/h. Increasing background noise resulted in a measurable impact on mean detection distances. The average reduction across all conditions was approximately 33% and 28% for approach speeds of 10 km/h and 20 km/h, respectively. In terms of accurately recognizing a stopped vehicle in a 20 to 0 km/h scenario, all sound conditions significantly outperformed the no-sound condition across both background noise conditions.