Search Results

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.

Lean applications in product development usually start with manufacturing due to the relative experience of measuring improvements and identifying wastes in physical settings. The full potential of lean implementation in any product development, however, can only be realized when applied throughout the process, starting with early process. Considering that the first and most essential principle in lean implementation is the characterization of value from the customer's perspective, it is imperative that the proper definition of value is realized at the beginning of the process. In addition, streaming and flowing of this customer's specified value should be realized throughout the process from start to finish. This paper discusses the application of lean principles to integrated design and manufacturing phases of the Product Development Process.

Typically, when someone needs to perform occasional towing tasks, such as towing a boat on a trailer, they have two choices. They can either purchase a larger, more powerful vehicle than they require for their regular usage, or they can rent a larger vehicle when they need to tow something. In this project, we propose a third alternative: a trailer with an on-board power supply, which can be towed by a small vehicle. This system requires a means of sensing how much power the trailer's power supply should provide, and an appropriate control system to provide this power. In this project, we design and model the trailer, a standard small car, and the control system, and evaluate the concept's feasibility. We have selected a suitable power source for the trailer, a DC motor, coupled directly to the trailer's single drive wheel, which allow us to dispense with the need for a differential.

While many current vehicle network systems for body bus applications use event triggered analysis processes, the deterministic point of view raises concerns about system timing due to message latency. This paper studies the latency performance characteristics of a typical body bus vehicle network using event triggered analysis over the CAN bus.

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.

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.

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 describes experiments conducted to determine the effect of multiple spark discharge ignition systems and spark plug electrode design on cold start performance of a dedicated E85 fueled vehicle. Tests were conducted using three different ignition configurations: OEM ignition and spark plugs, multiple spark discharge ignition with OEM spark plugs, and multiple spark discharge ignition with large gap circular electrode spark plugs. The multiple spark discharge ignition with OEM spark plugs showed a significant improvement in cold start performance over the OEM ignition, but the addition of the circular electrode spark plugs caused a decrease in cold start performance. The circular ground spark plugs did produce a higher ending coolant temperature than either of the other configurations.

Cylinder air/fuel ratio distribution is an important factor affecting the economy, power, vibration, and emissions of an internal combustion engine. Currently, production automobiles utilize an exhaust gas sensor located in the main exhaust stream in order to regulate air/fuel mixtures. By measuring the oxygen content of the exhaust gas for each cylinder independently, the degree of air/fuel variation between cylinders can be determined. This information can be used to determine the mixture quality of specific cylinders. Knowing these variances can lead to design changes in the intake and exhaust manifolds as well as better control of fuel metering which will improve the output of the engine. This study was carried out using a 1991 3.8L Buick V-6 engine with customized exhaust manifolds utilizing exhaust gas oxygen sensors for each cylinder in addition to the sensor located in the main combined exhaust gas stream. Production level, ZrO2 sensors were used for this experimental study.

This paper describes the experiments conducted to determine the effect of high energy multiple spark discharge (MSD) ignition systems and spark plug electrode design, on the cold start performance of a vehicle which was converted for dedicated operation on E85 (a blend of 85% ethanol and 15% gasoline) fuel. Tests were conducted using three different ignition configurations; original equipment manufacturer (OEM) ignition and spark plugs, high energy multiple spark discharge (MSD) ignition with OEM, J-type spark plugs, and high energy MSD ignition with surface gap electrode spark plugs. The high energy MSD ignition with OEM spark plugs showed a significant improvement in cold start performance over the OEM ignition. The addition of the surface gap spark plugs caused a decrease in cold start performance. Despite this, the surface gap spark plugs produced higher ending coolant temperature than the other configurations.

The safety of ground vehicles is a matter of critical importance. Vehicle safety is enhanced with the use of control systems that mitigate the effect of unachievable demands from the driver, especially demands for tire forces that cannot be developed. This paper presents the results of a smart tire prototyping and validation study, which is an investigation of a smart tire system that can be used as part of these mitigation efforts. The smart tire can monitor itself using in-tire sensors and provide information regarding its own tire forces and moments, which can be transmitted to a vehicle control system for improved safety. The smart tire is designed to estimate the three orthogonal tire forces and the tire aligning moment at least once per wheel revolution during all modes of vehicle operation, with high accuracy. The prototype includes two in-tire piezoelectric deformation sensors and a rotary encoder.

Vehicles are in contact with the road surface through tires, and the interaction at the tire-road interface is usually the major source of vibrations that is experienced by the passengers in the vehicle. Thus, it is critical to measure the vibrational characteristics of the tires in order to improve the safety and comfort of the passengers and also to make the vehicle quieter. The measurement results can also be used to validate numerical models. In this paper, Digital Image Correlation (DIC) as a non-contact technique is used to measure the dynamics of a racing tire in static and rolling conditions. The Kettering University FSAE car is placed on the dynamometer machine for this experiment. A pair of high-speed cameras is used to capture high-resolution images of the tire in a close-up view. The images are processed using DIC to obtain strain and displacement of the sidewall of the tire during rolling. The experiment is performed for various testing speeds.

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.

To improve the safety of automated driving, the paramount target of this intelligent system is to detect and segment the obstacle such as car and pedestrian, precisely. Object detection in self-driving vehicle has chiefly accomplished by making decision and detecting objects through each frame of video. However, there are diverse group of methods in both machine learning and machine vision to improve the performance of system. It is significant to factor in the function of the time in the detection phase. In other word, considering the inputs of system, which have been emitted from eclectic type of sensors such as camera, radar, and LIDAR, as time-varying signals, can be helpful to engross ‘time’ as a fundamental feature in modeling for forecasting the object, while car is moving on the way. In this paper, we focus on eliciting a model through the time to increase the accuracy of object detection in self-driving vehicles.

The automotive and aerospace industries are increasingly using the light-weight material to improve the vehicle performance. However, using light-weight material can increase the airborne and structure-borne noise. A special attention needs to be paid in designing the structures and measuring their dynamics. Conventionally, the structure is excited using an impulse hammer or a mechanical shaker and the response is measured using uniaxial or multi-axial accelerometers to obtain the dynamics of the structure. However, using contact-based transducers can mass load the structure and provide data at a few discrete points. Hence, obtaining the true dynamics of the structure conventionally can be challenging. In the past few years, stereo-photogrammetry and three-dimensional digital image correlation have received special attention in collecting operating data for structural analysis. These non-contact optical techniques provide a wealth of distributed data over the entire structure.

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.

The application of DO-178B for the verification and validation of the safety-critical aspects of a steer-by-wire sub-system of a vehicle by using a spiral development model is discussed. The project was performed within a capstone design course at Kettering University. Issues including lessons learned regarding requirements, specifications, testing, verification, and validation activities as required by DO-178B are summarized.