Search Results

Level 2 (L2) partial driving automation systems are rapidly emerging in the marketplace. L2 systems provide sustained automatic longitudinal and lateral vehicle motion control, reducing the need for drivers to continuously brake, accelerate and steer. Drivers, however, remain critically responsible for safely detecting and responding to objects and events. This paper summarizes variations of L2 systems (hands-on and/or hands-free) and considers human drivers’ roles when using L2 systems and for designing Human-Machine Interfaces (HMIs), including Driver Monitoring Systems (DMSs). In addition, approaches for examining potential unintended consequences of L2 usage and evaluating L2 HMIs, including field safety effect examination, are reviewed. The aim of this paper is to guide L2 system HMI development and L2 system evaluations, especially in the field, to support safe L2 deployment, promote L2 system improvements, and ensure well-informed L2 policy decision-making.

Motor vehicle crashes involving child Vulnerable Road Users (VRUs) remain a critical public health concern in the United States. While previous studies successfully utilized the crash scenario typology to examine traffic crashes, these studies focus on all types of motor vehicle crashes thus the method might not apply to VRU crashes. Therefore, to better understand the context and causes of child VRU crashes on the U.S. road, this paper proposes a multi-step framework to define crash scenario typology based on the Fatality Analysis Reporting System (FARS) and the Crash Report Sampling System (CRSS). A comprehensive examination of the data elements in FARS and CRSS was first conducted to determine elements that could facilitate crash scenario identification from a systematic perspective. A follow-up context description depicts the typical behavioral, environmental, and vehicular conditions associated with an identified crash scenario.

The Lane Change Task (LCT) provides a simple, scorable simulation of driving, and serves as a primary task in studies of driver distraction. It is widely accepted, but somewhat limited in functionality, a problem this project partially overcomes. In the Lane Change Task, subjects drive along a road with 3 lanes in the same direction. Periodically, signs appear, indicating in which of the 3 lanes the subject should drive, which changes from sign to sign. The software is plug-and-play for a current Windows computer with a Logitech steering/pedal assembly, even though the software was written 18 years ago. For each timestamp in a trial, the software records the steering wheel angle, speed, and x and y coordinates of the subject. A limitation of the LCT is that few characteristics of this useful software can be readily modified as only the executable code is available (on the ISO 26022 website), not the source code.

Making manned and remotely-controlled wheeled and tracked vehicles easier to drive, especially off-road, is of great interest to the U.S. Army. If vehicles are easier to drive (especially closed hatch) or if they are driven autonomously, then drivers could perform additional tasks (e.g., operating weapons or communication systems), leading to reduced crew sizes. Further, poorly driven vehicles are more likely to get stuck, roll over, or encounter mines or improvised explosive devices, whereby the vehicle can no longer perform its mission and crew member safety is jeopardized. HMI technology and systems to support human drivers (e.g., autonomous driving systems, in-vehicle monitors or head-mounted displays, various control devices (including game controllers), navigation and route-planning systems) need to be evaluated, which traditionally occurs in mission-specific (and incomparable) evaluations.

The automotive industry widely accepted the launch of electric vehicles in the global market, resulting in the emergence of many new areas, including battery health, inverter design, and motor dynamics. Maintaining the desired thermal stress is required to achieve augmented performance along with the optimal design of these components. The HVAC system controls the coolant and refrigerant fluid pressures to maintain the temperatures of [Battery, Inverter, Motor] in a definite range. However, identifying the prominent factors affecting the thermal stress of electric vehicle components and their effect on temperature variation was not investigated in real-time. Therefore, this article defines the vector electric vehicle thermal operating point (EVTHOP) as the first step with three elements [instantaneous battery temperature, instantaneous inverter temperature, instantaneous stator temperature].

Engaging in visual-manual tasks such as selecting a radio station, adjusting the interior temperature, or setting an automation function can be distracting to drivers. Additionally, if setting the automation fails, driver takeover can be delayed. Traditionally, assessing the usability of driver interfaces and determining if they are unacceptably distracting (per the NHTSA driver distraction guidelines and SAE J2364) involves human subject testing, which is expensive and time-consuming. However, most vehicle engineering decisions are based on computational analyses, such as the task time predictions in SAE J2365. Unfortunately, J2365 was developed before touch screens were common in motor vehicles.

Facial recognition software (FRS) is a form of biometric security that detects a face, analyzes it, converts it to data, and then matches it with images in a database. This technology is currently being used in vehicles for safety and convenience features, such as detecting driver fatigue, ensuring ride share drivers are wearing a face covering, or unlocking the vehicle. Public transportation hubs can also use FRS to identify missing persons, intercept domestic terrorism, deter theft, and achieve other security initiatives. However, biometric data is sensitive and there are numerous remaining questions about how to implement and regulate FRS in a way that maximizes its safety and security potential while simultaneously ensuring individual’s right to privacy, data security, and technology-based equality.

Engineering practice routinely involves decision making under uncertainty. Much of this decision making entails reconciling multiple pieces of information to form a suitable model of uncertainty. As more information is collected, one expectedly makes better and better decisions. However, conditional probability assessments made by human decision makers, as new information arrives does not always follow expected trends and instead exhibits inconsistencies. Understanding them is necessary for a better modeling of the cognitive processes taking place in their mind, whether it be the designer or the end-user. Doing so can result in better products and product features. Quantum probability has been used in the literature to explain many commonly observed deviations from the classical probability such as: question order effect, response replicability effect, Machina and Ellsberg paradoxes and the effect of positive and negative interference between events.

This work presents a method to estimate the human body orientation using 2D images from a person view; the challenge comes from the variety of human body poses and appearances. The method utilizes OpenPose neural network as a human pose detector module and depth sensing module. The modules work together to extract the body orientation from 2D stereo images. OpenPose is proven to be efficient in detecting human body joints, defined by COCO dataset, OpenPose can detect the visible body joints without being affected by backgrounds or other challenging factors. Adding the depth data for each point can produce rich information to the process of 3D construction for the detected humans. This 3D point’s setup can tell more about the body orientation and walking direction for example. The depth module used in this work is the ZED camera stereo system which uses CUDA for high performance depth computation.

Today, commercially available drones have limited use-cases in the rapidly evolving community. However, with advances in drone and software technology, it is possible to utilize these aerial machines to solve problems in a variety of industries such as mining, medical, construction, and law enforcement. For example, in order to reduce time of investigation, Indiana State Police are currently utilizing ad-hoc commercial drones to reconstruct crash scenes for insurance and legal purposes. In this paper, we illustrate how to effectively integrate drones for in-vehicle services and real-time prediction for automotive applications. In order to accomplish this, we first integrate simpler controls such as voice-commands to control the drone from the vehicle. Next, we build smart prediction software that monitors vehicle behavior and reacts in real-time to collisions.

Research in any field of study requires analysis and comparisons or real-time predictions to extract useful information. To prove that the results have practical potential, various filtering techniques and methodologies should be designed and implemented. Filters being a class of signal processing helps innovate new technologies with various kinds of outcomes, using filters there are always various methods to solve a problem. Considering the current COVID-19 situation, researchers are working on sequencing the novel coronavirus and the genomes of people afflicted with COVID-19 using CPUs and GPUs along with various filtering techniques. In this paper we are using a method of filter implementation to collect raw heart rate data samples from fingertip and ear lobe and process those results on CPUs and GPUs. Our method of implementation to collect raw heart rate data is using a photoplethysmography method.

Knee airbags (KABs) are one countermeasure in newer vehicles that could influence lower extremity (LEX) injury, the most frequently injured body region in frontal crashes. To determine the effect of KABs on LEX injury for drivers in frontal crashes, the analysis examined moderate or greater LEX injury (AIS 2+) in two datasets. Logistic regression considered six main effect factors (KAB deployment, BMI, age, sex, belt status, driver compartment intrusion). Eighty-five cases with KAB deployment from the Crash Injury Research and Engineering Network (CIREN) database were supplemented with 8 cases from the International Center for Automotive Medicine (ICAM) database and compared to 289 CIREN non-KAB cases. All cases evaluated drivers in frontal impacts (11 to 1 o’clock Principal Direction of Force) with known belt use in 2004 and newer model year vehicles. Results of the CIREN/ICAM dataset were compared to analysis of a similar dataset from NASS-CDS (5441 total cases, 418 KAB-deployed).

This SAE EDGE™ Research Report explores how the deployment of automated vehicles (AVs) will affect the insurance industry and the principles of liability that underly the structure of insurance in the US. As we trade human drivers for suites of sensors and computers, who (or what) is responsible when there is a crash? The owner of the vehicle? The automaker that built it? The programmer that wrote the code? Insurers have over 100 years of experience and data covering human drivers, but with only a few years’ worth of information on AVs – how can they properly predict the true risks associated with their deployment? Without an understanding of the nature and risks of AVs, how can the government agencies that regulate the insurance industry provide proper oversight? Do the challenges AVs present require a total reworking of our insurance and liability systems, or can our current structures be adapted to fit them with minor modifications?

This work presents a method for estimating human body orientation using a combination of convolutional neural network (CNN) and stereo camera in real time. The approach uses the CNN model to predict certain human body keypoints then transforms these points into a 3D space using the stereo vision system to estimate the body orientations. The CNN module is trained to estimate the shoulders, the neck and the nose positions, detecting of three points is required to confirm human detection and provided enough data to translate the points into 3D space.

An existing challenge in current state-of-the-art autonomous vehicles is the process of safely transferring control from autonomous driving mode to manual mode because the driver may be distracted with secondary tasks. Such distractions may impair a driver’s situational awareness of the driving environment which will lead to fatal outcomes during a handover. Current state-of-the-art vehicles notify a user of an imminent handover via auditory, visual, and physical alerts but are unable to improve a driver’s situational awareness before a handover is executed. The overall goal of our research team is to address the challenge of providing a driver with relevant information to regain situational awareness of the driving task. In this paper, we introduce a novel approach to estimating a driver’s visual focus of attention using a 2D RGB camera as input to a Multi-Input Convolutional Neural Network with shared weights. The system was validated in a realistic driving scenario.

In-vehicle infotainment (IVI) platforms are getting increasingly connected. Besides OEM apps and services, the next generation of IVI platforms are expected to offer integration of third-party apps. Under this anticipated business model, vehicular sensor and event data can be collected and shared with selected third-party apps. To accommodate this trend, Google has been pushing towards standardization among proprietary IVI operating systems with their Android Automotive platform which runs natively on the vehicle’s IVI platform. Unlike Android Auto’s limited functionality of display-projecting certain smartphone apps to the IVI screen, Android Automotive will have access to the in-vehicle network (IVN), and will be able to read and share various vehicular sensor data with third-party apps. This increased connectivity opens new business opportunities for both the car manufacturer as well as third-party businesses, but also introduces a new attack surface on the vehicle.

To ensure ride comfort, the dynamic characteristics, such as natural frequencies, of a vehicle is often tuned to a specific value by managing the magnitude and location of some masses and/or configuration of stiffeners without sacrificing the structural strength and overall fuel performance of the vehicle. We first formulate the mathematical statement of the problem in a constrained eigenvalue form. Optimal solutions are sought using various finite element techniques. A novel methodology involving genetic algorithm and Newton’s iterative method is developed to solve the constrained eigenvalue problems. Several examples, including discrete and continuous systems, are presented to demonstrate the effectiveness and accuracy of the proposed methodology. The strategy of managing the mass location and distribution to target a preferred natural frequency or frequencies is given in the conclusion.

Privacy has been a rising concern. The European Union has established a privacy standard called General Data Protection Regulation (GDPR) in May 2018. Furthermore, the Facebook-Cambridge Analytica data incident made headlines in March 2018. Data collection from vehicles by OEM platforms is increasingly popular and may offer OEMs new business models but it comes with the risk of privacy leakages. Vehicular sensor data shared with third-parties can lead to misuse of the requested data for other purposes than stated/intended. There exists a relevant regulation document introduced by the Alliance of Automobile Manufacturers (“Auto Alliance”), which classifies the vehicular sensors used for data collection as covered and non-sensitive parameters.

The goal of this project was to investigate how to make driver distraction state classification more efficient by applying selected machine learning techniques to existing datasets. The data set used in this project included both overt driver behavior measures (e.g., lane keeping and headway measures) and indices of internal cognitive processes (e.g., driver situation awareness responses) collected under four distraction conditions, including no-distraction, visual-manual distraction only, cognitive distraction only, and dual distraction conditions. The baseline classification method that we employed was a support vector machine (SVM) to first identify driver states of visual-manual distraction and then to identify any cognitive-related distraction among the visual-manual distraction cases and other non-visual manual distraction cases.

Future fully autonomous and partially autonomous cars equipped with Advanced Driver Assistant Systems (ADAS) should assure safety for the pedestrian. One of the critical tasks is to determine if the pedestrian is crossing the road in the path of the ego-vehicle, in order to issue the required alerts for the driver or even safety breaking action. In this paper, we investigate the use of 2D pose estimators to determine the direction and speed of the pedestrian crossing the road in front of a vehicle. Pose estimation of body parts, such as right eye, left knee, right foot, etc… is used for determining the pedestrian orientation while tracking these key points between frames is used to determine the pedestrian speed. The pedestrian orientation and speed are the two required elements for the basic path estimation.