Automotive Engineering Commons^™

Application Of Fusion Based Deep Learning Models To Improve Millimeter Wave Beamforming, Abishek Subramanian

Dissertations, Master's Theses and Master's Reports

This study addresses the challenge of selecting millimeter Wave (mmWave) beamforming pairs for vehicle-to-infrastructure (V2I) communication, to mitigate latency in highly dynamic vehicular environments. We investigate the use of out-of-band sensor data as side information to model mmWave ray tracing paths and predicting a subset of top-K optimal beamforming pairs for efficient and low-latency searches. Unimodal-Fusion Deep Learning (F-DL) networks was applied to enhance mmWave beamforming process. We started by first investigating the centralized architecture, and then explored a novel distributed architecture through federated learning to minimize resource and latency overheads. The distributed architecture incorporates two biased client selection strategies: …

Hybrid Sensors, Kv Santhosh

Technical Collection

With the ever increasing demand of quality product, efficient automation is of prime requirement. Automation involves the process of monitoring and control. Efficient monitoring is only possible with the best sensing mechanism. Conventional characteristics of sensors like accuracy, range, sensitivity, etc is not just sufficient for achieving the desired objective. Characteristics like cooperation, competition and complementary is the need of the hour.

Concept of a hybrid sensor involves the implementation of multi-sensor system architecture, such that each of the sensors will compliment and/or cooperate and/or compete with each of the other sensor to achieve the complete and efficient monitoring.

Research …

Modernization Of Scienttific Mathematics Formula In Technology, Iwasan D. Kejawa Ed.D, Prof. Iwasan D. Kejawa Ed.D

Department of Mathematics: Faculty Publications

Abstract
Is it true that we solve problem using techniques in form of formula? Mathematical formulas can be derived through thinking of a problem or situation. Research has shown that we can create formulas by applying theoretical, technical, and applied knowledge. The knowledge derives from brainstorming and actual experience can be represented by formulas. It is intended that this research article is geared by an audience of average knowledge level of solving mathematics and scientific intricacies. This work details an introductory level of simple, at times complex problems in a mathematical epidermis and computability and solvability in a Computer Science. …

A Deep Learning-Based Automatic Object Detection Method For Autonomous Driving Ships, Ojonoka Erika Atawodi

Master's Theses

An important feature of an Autonomous Surface Vehicles (ASV) is its capability of automatic object detection to avoid collisions, obstacles and navigate on their own.

Deep learning has made some significant headway in solving fundamental challenges associated with object detection and computer vision. With tremendous demand and advancement in the technologies associated with ASVs, a growing interest in applying deep learning techniques in handling challenges pertaining to autonomous ship driving has substantially increased over the years.

In this thesis, we study, design, and implement an object recognition framework that detects and recognizes objects found in the sea. We first curated …

Evaluating Driving Performance Of A Novel Behavior Planning Model On Connected Autonomous Vehicles, Keyur Shah

Honors Scholar Theses

Many current algorithms and approaches in autonomous driving attempt to solve the "trajectory generation" or "trajectory following” problems: given a target behavior (e.g. stay in the current lane at the speed limit or change lane), what trajectory should the vehicle follow, and what inputs should the driving agent apply to the throttle and brake to achieve this trajectory? In this work, we instead focus on the “behavior planning” problem—specifically, should an autonomous vehicle change lane or keep lane given the current state of the system?

In addition, current theory mainly focuses on single-vehicle systems, where vehicles do not communicate with …

Nonlinear Least Squares 3-D Geolocation Solutions Using Time Differences Of Arrival, Michael V. Bredemann

Mathematics & Statistics ETDs

This thesis uses a geometric approach to derive and solve nonlinear least squares minimization problems to geolocate a signal source in three dimensions using time differences of arrival at multiple sensor locations. There is no restriction on the maximum number of sensors used. Residual errors reach the numerical limits of machine precision. Symmetric sensor orientations are found that prevent closed form solutions of source locations lying within the null space. Maximum uncertainties in relative sensor positions and time difference of arrivals, required to locate a source within a maximum specified error, are found from these results. Examples illustrate potential requirements …

Quantitative Performance Assessment Of Lidar-Based Vehicle Contour Estimation Algorithms For Integrated Vehicle Safety Applications, David M. Mothershed

Electronic Theses and Dissertations

Many nations and organizations are committing to achieving the goal of `Vision Zero' and eliminate road traffic related deaths around the world. Industry continues to develop integrated safety systems to make vehicles safer, smarter and more capable in safety critical scenarios. Passive safety systems are now focusing on pre-crash deployment of restraint systems to better protect vehicle passengers. Current commonly used bounding box methods for shape estimation of crash partners lack the fidelity required for edge case collision detection and advanced crash modeling. This research presents a novel algorithm for robust and accurate contour estimation of opposing vehicles. The presented …

Gesture Based Control Of Semi-Autonomous Vehicles, Brian Sanders

Computational Modeling & Simulation Engineering Theses & Dissertations

The objective of this investigation is to explore the use of hand gestures to control semi-autonomous vehicles, such as quadcopters, using realistic, physics based simulations. This involves identifying natural gestures to control basic functions of a vehicle, such as maneuvering and onboard equipment operation, and building simulations using the Unity game engine to investigate preferred use of those gestures. In addition to creating a realistic operating experience, human factors associated with limitations on physical hand motion and information management are also considered in the simulation development process. Testing with external participants using a recreational quadcopter simulation built in Unity was …

Experimental And Numerical Simulation Of Split Hopkinson Pressure Bar Test On Borosilicate Glass, Mayank K. Bagaria

Dissertations, Master's Theses and Master's Reports

This study is an extension to the design of ceramic materials component exposed to bullet impact. Owing to the brittle nature of ceramics upon bullet impact, shattered pieces behave as pellets flying with different velocities and directions, damaging surrounding components. Testing to study the behavior of ceramics under ballistic impact can be cumbersome and expensive. Modeling the set-up through Finite Element Analysis (FEA) makes it economical and easy to optimize. However, appropriately incorporating the material in modeling makes laboratory testing essential. Previous efforts have concentrated on simulating crack pattern developed during 0.22 caliber pellet impact on Borosilicate glass. A major …

Vehicle Pseudonym Association Attack Model, Pierson Yieh

Master's Theses

With recent advances in technology, Vehicular Ad-hoc Networks (VANETs) have grown in application. One of these areas of application is Vehicle Safety Communication (VSC) technology. VSC technology allows for vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communications that enhance vehicle safety and driving experience. However, these newly developing technologies bring with them a concern for the vehicular privacy of drivers. Vehicles already employ the use of pseudonyms, unique identifiers used with signal messages for a limited period of time, to prevent long term tracking. But can attackers still attack vehicular privacy even when vehicles employ a pseudonym change strategy? The major contribution …

Autonomous Cars And Driverless Lethal Autonomy, Nyagudi Musandu Nyagudi

Nyagudi M Nyagudi

“The small picture” - make an advanced autonomous /driverless car. Lots of algorithms, sensors, computers and other gizmos. Now get it to take you to work, park itself and seamlessly run your family errands around the city. Taking grandma to the doctor for the medical check-up, getting the children from school, etc. With Radar, Lidar and other sensors, the car steering with ease through the traffic, no driver to pay, that is another plus, fuel/energy efficiency, yet another plus. It is a bold new world and the sky is the limit. Without the resolution of “small picture” issues there is …

A Quantitative Investigation Of The Water Condensation Inside Tubes Of Compact Charge Air Cooler, Robin Cash

Dissertations, Master's Theses and Master's Reports

To address the need of increasing fuel economy requirements, automotive Original Equipment Manufacturers (OEMs) are increasing the number of turbocharged engines in their powertrain line-ups. The turbine-driven technology uses a forced induction device, which increases engine performance by increasing the density of the air charge being drawn into the cylinder. Denser air allows more fuel to be introduced into the combustion chamber, thus increasing engine performance. During the compression process, the air is heated to temperatures that can cause pre-ignition, resulting in reduced engine functionality. The introduction of the charge air cooler (CAC) is therefore, necessary to extract heat from …

Inkjet Printing: Facing Challenges And Its New Applications In Coating Industry, Sadegh Poozesh

Theses and Dissertations--Mechanical Engineering

This study is devoted to some of the most important issues for advancing inkjet printing for possible application in the coating industry with a focus on piezoelectric droplet on demand (DOD) inkjet technology. Current problems, as embodied in liquid filament breakup along with satellite droplet formation and reduction in droplet sizes, are discussed and then potential solutions identified. For satellite droplets, it is shown that liquid filament break-up behavior can be predicted by using a combination of two pi-numbers, including the Weber number, We and the Ohnesorge number, Oh, or the Reynolds number, Re, and the Weber number, …