Search Results

Objection detection using a camera sensor is essential for developing Advanced Driver Assistance Systems (ADAS) and Autonomous Driving (AD) vehicles. Due to the recent advancement in deep Convolution Neural Networks (CNNs), object detection based on CNNs has achieved state-of-the-art performance during daytime. However, using an RGB camera alone in object detection under poor lighting conditions, such as sun flare, snow, and foggy nights, causes the system's performance to drop and increases the likelihood of a crash. In addition, the object detection system based on an RGB camera performs poorly during nighttime because the camera sensors are susceptible to lighting conditions. This paper explores different pedestrian detection systems at low-lighting conditions and proposes a sensor-fused pedestrian detection system under low-lighting conditions, including nighttime. The proposed system fuses RGB and infrared (IR) thermal camera information.

The sound quality of automotive interiors is one of the critical factors regarding customer satisfaction. As electric vehicles (EVs) rapidly rise in popularity, the known literature on sound qualities of internal combustion engine (ICE) automotive interiors has become less relevant. Because of this, comparing and contrasting 'the sound qualities of EV and ICE vehicles is essential to have the proper foundation for studying automotive noise quality in the future. In this paper, we aim to benchmark the major differences between an EV and an ICE automobile regarding interior sound quality. This study seeks to understand basic sound engineering characteristics and how they differ between the two types of vehicles. We also analyzed the public's preferences when it comes to the two types of cars.

Since the popularization of the Electric Vehicle (EV) there has been a large movement of consumers, governments, and the automotive industry due to its environmentally friendly characteristics. Unlike an IC engine, the batteries use multitudes of rare earth minerals and complex manufacturing processes which in some cases have been shown to produce as many emissions as an ICE vehicle over its entire lifespan. Another unnoticed important environmental concern has been the final recycling and disposal of the power train after its use. Unlike an ICE engine, which can be melted down or re-used, recycling batteries are much more difficult. In most cases the recycling process and the byproducts produced can be very harmful to the environment. This paper aims to be a complete cradle-to-grave analysis of all emissions produced in the life of an EV battery.

Data-driven modeling can help improve understanding of the governing equations for systems that are challenging to model. In the current work, the Sparse Identification of Nonlinear Dynamical systems (SINDy) is used to predict the dynamic behavior of dynamic problems for NVH applications. To show the merit of the approach, the paper demonstrates how the equations of motions for linear and nonlinear multi-degree of freedom systems can be obtained. First, the SINDy method is utilized to capture the dynamic behavior of linear systems. Second, the accuracy of the SINDy algorithm is investigated with nonlinear dynamic systems. SINDy can output differential equations that correspond to the data. This method can be used to find equations for dynamical systems that have not yet been discovered or to study current systems to compare with our current understanding of the dynamical system.

As automated driving becomes more common, simulation of vehicle dynamics and control scenarios are increasingly important for investigating motion control approaches. In this work, a study of the differences between the Pure Pursuit and Stanley autonomous vehicle controllers, based on vehicle dynamics responses, is presented. Both are geometric controllers that use only immediate vehicle states, along with waypoint data, to control a vehicle’s future direction as it proceeds from point to point, and both are among the most popular lateral controllers in use today. The MATLAB Automated Driving Toolbox is employed to implement and virtually test the Pure Pursuit and Stanley lateral controllers in different driving scenarios. These include low intensity scenarios such as city driving, and emergency maneuvers such as the moose test.

Much development in the automotive industry relates to the use of high-content ethanol blended fuels to reduce the emissions produced by on-road engines/vehicles. However, less research has been done on the effect of operating small off-road engines (SORE) on high-blend ethanol fuels without substantial modifications. Most manufacturers of such engines only certify proper operation on low content ethanol blends such as E10 (10% ethanol, 90% gasoline by volume). This paper focuses on the use of E77 fuel in a small off-road engine which is speed-governed. Such engines are commonly used in lawn mowers, small recreational vehicles, or other equipment. The exhaust emissions and performance of the engine were evaluated using the EPA 6-mode duty cycle for small recreational engines where testing and analysis followed the recommendations of SAE J1088. This test cycle consisted of operating the engine at steady state load points using a fixed engine speed.

Object avoidance for autonomous driving is a vital factor in safe driving. When a vehicle travels from any random start places to any target positions in the milieu, an appropriate route must prevent static and moving obstacles. Having the accurate depth of each barrier in the scene can contribute to obstacle prevention. In recent years, precise depth estimation systems can be attributed to notable advances in Deep Neural Networks and hardware facilities/equipment. Several depth estimation methods for autonomous vehicles usually utilize lasers, structured light, and other reflections on the object surface to capture depth point clouds, complete surface modeling, and estimate scene depth maps. However, estimating precise depth maps is still challenging due to the computational complexity and time-consuming process issues. On the contrary, image-based depth estimation approaches have recently come to attention and can be applied for a broad range of applications.

Driving comfort and automotive product quality are strongly associated with the vibration that is transmitted to the occupants of a vehicle at the points of contact to the human body, including the seat, steering wheel, and pedals. Of these three contact locations, the seats have the most general importance, as all occupants of a vehicle experience seat vibration. Particularly relevant to driving comfort is the way in which vehicle occupants perceive seat vibration, which may be different than expected considering sensor measured vibration levels. Much of the interest in seat vibration has been focused on internal combustion engine powertrain vibration, especially idle vibration. However, electrification of vehicles changes the focus from low frequency idle vibration to higher frequency vibration sources.

Environmental perception is considered an essential module for autonomous driving and Advanced Driver Assistance System (ADAS). Recently, deep Convolutional Neural Networks (CNNs) have become the State-of-the-Art with many different architectures in various object detection problems. However, performances of existing CNNs have been dropping when detecting small objects at a large distance. To deploy any environmental perception system in real world applications, it is important that the system achieves high accuracy regardless of the size of the object, distance, and weather conditions. In this paper, a robust sensor fused object detection system is proposed by utilizing the advantages of both vision and automotive radar sensors. The proposed system consists of three major components: 1) the Coordinate Conversion module, 2) Multi level-Sensor Fusion Detection (MSFD) system, and 3) Temporal Correlation filtering module.

Forward collision warning is one of the most challenging concerns in the safety of autonomous vehicles. A cooperation between many sensors such as LIDAR, Radar and camera helps to enhance the safety. Apart from the importance of having a reliable object detector, the safety system should have requisite capabilities to make reasonable decisions in the moment. In this work, we concentrate on detecting front vehicles of autonomous cars using a monocular camera, beyond only a detection method. In fact, we devise a solution based on a cooperation between a deep object detector and a reinforcement learning method to provide forward collision warning signals. The proposed method models the relation between acceleration, distance and collision point using the area of the bounding box related to the front vehicle. An agent of learning automata as a reinforcement learning method interacts with the environment to learn how to behave in eclectic hazardous situations.

As advanced vehicle controls and autonomy become mainstream in the automotive industry, the need to employ traditional mathematical models and control strategies arises for the purpose of simulating autonomous vehicle handling maneuvers. This study focuses on lane change maneuvers for autonomous vehicles driving at low speeds. The lane change methodology uses PID (Proportional-Integral-Derivative) controller to command the steering wheel angle, based on the yaw motion and lateral displacement of the vehicle. The controller was developed and tested on a bicycle model of an electric vehicle (a Chevrolet Bolt 2017), with the implementation done in MATLAB/Simulink. This simple mathematical model was chosen in order to limit computational demands, while still being capable of simulating a smooth lane change maneuver under the direction of the car’s mission planning module at modest levels of lateral acceleration.

The fatal automobile accidents can be attributed to fatigued and distracted driving by drivers. Driver Monitoring Systems alert the distracted drivers by raising alarms. Most of the image based driver drowsiness detection systems face the challenge of failure proof performance in real time applications. Failure in face detection and other important part (eyes, nose and mouth) detections in real time cause the system to skip detections of blinking and yawning in few frames. In this paper, a real time robust and failure proof driver drowsiness detection system is proposed. The proposed system deploys a set of detection systems to detect face, blinking and yawning sequentially. A robust Multi-Task Convolutional Neural Network (MTCNN) with the capability of face alignment is used for face detection. This system attained 97% recall in the real time driving dataset collected. The detected face is passed on to ensemble of regression trees to detect the 68 facial landmarks.

Due to the nearly silent operation of an electric motor, it is difficult for pedestrians to detect an approaching electric vehicle. To address this safety concern, the National Highway Traffic Safety Administration issued the Federal Motor Vehicle Safety Standard (FMVSS) No. 141, “Minimum Sound Requirements for Hybrid and Electric Vehicles”. This FMVSS 141 standard requires the measurement of electric vehicle noise according to certain test protocols; however, performing these tests can be difficult since inconsistent results can occur in the presence of transient background noise. Methods to isolate background noise during static sound measurements have already been established, though these methods are not directly applicable to a pass-by noise test where neither the background noise nor the vehicle itself as it travels past the microphone produce stationary sound signals.

Automakers looking to remake their traditional vehicle line-up into autonomous vehicles, Noise, Vibration, and Harshness (NVH) considerations for autonomous vehicles are soon to follow. While traditional NVH considerations still must be applied to carry-over systems, additional components are required for an autonomous vehicle to operate. These additional components needed for autonomy also require NVH analysis and optimization. Autonomous vehicles rely on a suite of sensors, including Light Detection and Ranging (LiDAR) and cameras placed at optimal points on the vehicle for maximum coverage and utilization. In this study, the NVH considerations of autonomous vehicles are examined, focusing on the additional perception equipment installed in autonomous vehicles.

Lane marks are an important aspect for autonomous driving. Autonomous vehicles rely on lane mark information to determine a safe and legal path to drive. In this paper an approach to estimate lane lines on straight or slightly curved roads using a LiDAR unit for autonomous vehicles is presented. By comparing the difference in elevation of LiDAR channels, a drivable region is defined. The presented approach used in this paper differs from previous LiDAR lane line detection methods by reducing the drivable region from three to two dimensions exploring only the x-y trace. In addition, potential lane markings are extracted by filtering a range of intensity values as opposed to the traditional approach of comparing neighboring intensity values. Further, by calculating the standard deviation of the potential lane markings in the y-axis, the data can be further refined to specific points of interest.

This paper aims to study the NVH and acoustic performance of a 3-phase AC induction motor in order to develop an approach to reduce the magnetic component of noise from an electric motor in an electric vehicle (EV). The final goal of this project is to reduce the magnetic component of sound from the motor by making modifications to the end bracket of the motor housing. EVs are being considered the future of mobility mainly due to the fact that they are environment-friendly. As many companies are already investing in this technology, electric drives are set to become extremely popular in the years to come. The heart of an EV is its motor. Modern electric vehicles are quiet, furthermore with the lack of an IC engine to mask most sounds from other components, the sound from the electric motor and other auxiliary parts become more prominent.

For virtual simulation of the vehicle attributes such as handling, durability, and ride, an accurate representation of pneumatic tire behavior is very crucial. With the advancement in autonomous vehicles as well as the development of Driver Assisted Systems (DAS), the need for an Intelligent Tire Model is even more on the increase. Integrating sensors into the inner liner of a tire has proved to be the most promising way in extracting the real-time tire patch-road interface data which serves as a crucial zone in developing control algorithms for an automobile. The model under development in Kettering University (KU-iTire), can predict the subsequent braking-traction requirement to avoid slip condition at the interface by implementing new algorithms to process the acceleration signals perceived from an accelerometer installed in the inner liner on the tire.

This paper documents the electrical infrastructure design of a Hybrid Go Kart competition vehicle which includes a dual Fuel Cell power system, Ultra Capacitors for energy storage, and a dual AC induction motor capable of independent drive. The Kart was built primarily to compete in the 2009 Formula Zero international event. This paper emphasized the vehicle model and control strategy as a result of three (3) graduate student research projects. The vehicle was fabricated and tested but did not participate in the race competition since the race organization folded. The vehicle model was developed in Simulink to determine whether the fuel cell and ultra-capacitor combination will be sufficient for peak transient power requirement of 14 kW. The vehicle’s functional description and performance specifications are documented including the integration of the fuel cell power modules, energy storage system, power converters, and AC motor and motor controllers.

A numerical and experimental study of the use of air motion control, piston bowl shape, and injector configuration on combustion and emissions in diesel engines has been conducted. The objective of this study is to investigate the use of flow control within the piston bowl during compression to enhance fuel air mixing to achieve a uniform air-fuel mixture to reduce soot and NO emissions. In addition to flow control different piston bowl geometries and injector spray angles have been considered and simulated using three-dimensional computational fluid dynamics and experiments. The results include cylinder pressure and emissions measurements and contour plots of fuel mass fraction, soot, and NO. The results show that soot and NO emissions can be reduced by proper flow control and piston bowl design.

Most of the present EV on-board chargers utilize a three-stage design, e.g., AC/DC rectifier, DC to high-frequency AC inverter, and AC to DC rectifier, which limits the wall-to-battery efficiency to ∼94%. To further increase the efficiency and power density, a matrix converter is an excellent candidate directly converting grid AC to high-frequency AC thereby saves one stage. However, its control complexity and the high cost of building the back-to-back switches are barriers its acceptance. Instead, this paper adopts the 650V E-mode GaN HEMTs to build a level-2 on-board charger using the indirect matrix topology. The input voltage is 80∼260VAC, the battery voltage is 200∼500VDC and the rated power is 7.2kW. Variable switching frequency is combined with phase-shift control to realize the zero-voltage switching. To further increase the system efficiency, four GaN HEMTs are paralleled to form one switching module with a novel gate-drive technology.