Browsing by Author "Stowe, Loren"

Now showing 1 - 6 of 6
  • Thumbnail Image
    Application of Proximity Sensors to In-vehicle Data Acquisition Systems
    Krothapalli, Ujwal; Stowe, Loren; Doerzaph, Zachary R.; Petersen, Andy (National Surface Transportation Safety Center for Excellence, 2018-05-02)
    Naturalistic driving studies rely on human data reductionists to manually review and annotate driving behaviors. This work is time-consuming, and algorithms that could scan and categorize video data could make the data reduction process faster and more efficient. This report describes research to develop pose estimation methods that can be applied to drivers in naturalistic settings. Three methods were explored: (1) a depth-sensor-based pose estimation; (2) a deformable parts-based model; and (3) a tiny-image-based driver activity classifier. The tiny-image-based approach was chosen as the final solution and tested using the VTTIMLP01 dataset, a collection of about 80,000 images from 25 participants in naturalistic driving and simulated naturalistic driving conditions. The model was applied to approximately 50,000 images from the dataset covering seven activity classes: Eating/Drinking, Talking, Visor, Center Stack, Texting, One Hand on the Wheel, and Both Hands on the Wheel. The model, without any aspect ratio changes to the input image, was able to predict the activity classes with an overall 70% accuracy. To obtain better accuracies for individual activity classes, a separate model was built for each class, which resulted in a model with an overall accuracy of 74%. The Texting class had the poorest class accuracy (56%) due to the foreshortening effect on the limbs in the given camera angle. The One Hand on the Wheel class had the best class accuracy (96%).
  • Thumbnail Image
    Assessing Effects of Object Detection Performance on Simulated Crash Outcomes for an Automated Driving System
    Galloway, Andrew Joseph (Virginia Tech, 2023-07-11)
    Highly Automated Vehicles (AVs) have the capability to revolutionize the transportation system. These systems have the possibility to make roads safer as AVs do not have limitations that human drivers do, many of which are common causes of vehicle crashes (e.g., distraction or fatigue) often defined generically as human error. The deployment of AVs is likely to be very gradual however, and there will exist situations in which the AV will be driving in close proximity with human drivers across the foreseeable future. Given the persistent crash problem in which the makority of crashes are attributed to driver error, humans will continue to create potential collision scenarios that an AV will be expected to try and avoid or mitigate if developed appropriately. The absence of unreasonable risk in an AVs ability to comprehend and react in these situations is referred to as operational safety. Unlike advanced driver assistance systems (ADAS), highly automated vehicles are required to perform the entirety of the dynamic driving task (DDT) and have a greater responsibility to achieve a high level of operational safety. To address this concern, scenario-based testing has increasingly become a popular option for evaluating AV performance. On a functional level, an AV typically consists of three basic systems: the perception system, the decision and path planning system, and vehicle motion control system. A minimum level of performance is needed in each of these functional blocks to achieve an adequate level of operational safety. The goal of this study was to investigate the effects that perception system performance (i.e., target object state errors) has on vehicle operational safety in collision scenarios similar to that created by human drivers. In the first part of this study, recent annual crash data was used to define a relevant crash population of possible scenarios involving intersections that an AV operating as an urban taxi may encounter. Common crash maneuvers and characteristics were combined to create a set of testing scenarios that represent a high iii percentage of the overall crash population. In the second part of this study, each test scenario was executed using an AV test platform during closed road testing to determine possible real-world perception system performance. This provided a measure of the error in object detection measurements compared to the ideal (i.e., where a vehicle was detected to be compared to where it actually was). In the third part of this study, a set of vehicle simulations were performed to assess the effect of perception system performance on crash outcomes. This analysis simulated hypothetical crashes between an AV and one other collision partner. First an initial worst-case impact configuration was defined and was based on injury outcomes seen in crash data. The AV was then simulated to perform a variety of evasive maneuvers based on an adaptation of a non-impaired driver model. The impact location and orientation of the collision partner was simulated as two states: one based on the object detection of an ideal perception system and the other based on the object detection of the perception system from the AV platform used during the road testing. For simulations in which the two vehicles contacted each other, a planar momentum-impulse model was used for impact modeling and injury outcomes were predicted using an omni-directional injury model taken from recent literature. Results from this study indicate that errors in perception system measurements can change the perceived occupant injury risk within a crash. Sensitivity was found to be dependent on the specific crash type as well as what evasive maneuver is taken. Sensitivities occurred mainly due to changes in the principal direction of force for the crash and the interaction within the injury risk prediction curves. In order to achieve full operational safety, it will likely be important to understand the influence that each functional system (perception, decision, and control) may have on AV performance in these crash scenarios.
  • Thumbnail Image
    The Impact of Line-of-Sight and Connected Vehicle Technology on Mitigating and Preventing Crash and Near-Crash Events
    Herbers, Eileen; Doerzaph, Zachary; Stowe, Loren (MDPI, 2024-01-12)
    Line-of-sight (LOS) sensors developed in newer vehicles have the potential to help avoid crash and near-crash scenarios with advanced driving-assistance systems; furthermore, connected vehicle technologies (CVT) also have a promising role in advancing vehicle safety. This study used crash and near-crash events from the Second Strategic Highway Research Program Naturalistic Driving Study (SHRP2 NDS) to reconstruct crash events so that the applicable benefit of sensors in LOS systems and CVT can be compared. The benefits of CVT over LOS systems include additional reaction time before a predicted crash, as well as a lower deceleration value needed to prevent a crash. This work acts as a baseline effort to determine the potential safety benefits of CVT-enabled systems over LOS sensors alone.
  • Thumbnail Image
    Impacts of Connected Vehicle Technology on Automated Vehicle Safety
    Herbers, Eileen; Stowe, Loren (SAFE-D: Safety Through Disruption National University Transportation Center, 2022-05)
    Connected vehicle technologies have a promising role in advancing vehicle safety, but just how much of an impact can connected vehicles have on driver safety? This study uses crash and near-crash events from the Second Strategic Highway Research Program Naturalistic Driving Study (SHRP2 NDS) to reconstruct crash events so that the benefit of line-of-sight (LOS) systems and connected vehicle technologies (CVT) can be compared. The benefits of CVT over LOS systems includes additional reaction time before a predicted crash, as well as a lower deceleration value needed to prevent a crash. These values were then used to predict the probability of severe injury for any crashes that could occur. This work acts as a baseline effort to determine the potential safety benefits of CVT-enabled systems over line-of-sight technologies alone.
  • Thumbnail Image
    Investigation of ADAS/ADS Sensor and System Response to Rainfall Rate
    Cowan, Jonathan B.; Stowe, Loren (National Surface Transportation Safety Center for Excellence, 2024-08-23)
    Advanced driver assistance systems (ADAS) and automated driving systems (ADS) rely on a variety of sensors to detect objects in the driving environment. It is well known that rain has a negative effect on sensors, whether by distorting the inputs via water film on the sensor or attenuating the signals during transmission. However, there is little research under controlled and dynamic test conditions exploring how rainfall rate affects sensor performance. Understanding how precipitation may affect the sensor’s performance, in particular the detection and state estimation performance, is necessary for safe operation of the ADAS/ADS. This research strove to characterize how rainfall rate affects sensor performance and to provide insight into the effect it may have on overall system performance. The team selected a forward collision warning/automatic emergency braking scenario with a vehicle and surrogate vulnerable road user (VRU) targets. The research was conducted on the Virginia Smart Roads’s weather simulation test area, which can generate various simulated weather conditions, including rain, across a test range of 200 m. The selected sensors included camera, lidar, and radar, which are the primary sensing modalities used in ADAS and ADS. The rain rates during testing averaged 21 mm/h and 40 mm/h. Overall, the data backed up the expected trend that increasing rainfall rate worsens detection performance. The reduced detection probability was most prominent at longer ranges, thus reducing the effective range of the sensor. The lidars showed a general linear trend of 1% reduction in range per 1 mm/h of rainfall with some target type dependence. The long-range and short-range cameras show at least a 60% reduction in detection range at 40 mm/h. The object camera, which only detected the vehicle target, showed better performance with only a 20% reduction in range at 40 mm/h, which may be due to the underlying ADAS specific detection model. For vehicles, the radars typically showed a linear drop in detection range performance with an approximately 20% reduction in range at 40 mm/h rainfall rate. The VRU target showed a larger decrease in detection range compared to the vehicle target due likely to the smaller overall signal the VRU target returns.
  • Thumbnail Image
    Naturalistic Driving Study: Technical Coordination and Quality Control (SHRP 2 Report S2-S06-RW-1)
    Dingus, Thomas A.; Hankey, Jonathan M.; Antin, Jonathan F.; Lee, Suzanne E.; Eichelberger, Lisa; Stulce, Kelly E.; McGraw, Doug; Perez, Miguel A.; Stowe, Loren (Transportation Research Board, 2015)