Navigation, Guidance, Control, and Dynamics Commons^™

Data-Driven Discovery Of Finite-Dimensional Koopman Operator For Modeling And Control Of Uncrewed Ground Vehicles, Ajinkya Joglekar

All Dissertations

This dissertation advances data-driven modeling and adaptive control techniques for Uncrewed Ground Vehicles (UGVs), with a focus on autonomy in mission-critical and safety sensitive environments. UGVs are deployed across a wide spectrum of domains, from structured manufacturing shop floors to unstructured off-road terrains, including planetary exploration, precision agriculture, and disaster response. These platforms, operating in dull, dirty, and dangerous conditions, demand autonomy that is both adaptable and robust. While traditional model-based control methods offer interpretability and robustness, they struggle with unmodeled dynamics, parameter variations, and integration of high-dimensional sensing. Conversely, modern machine learning approaches can directly exploit sensory data but …

Resilient Control Framework For Ev Motor Drive System Subject To Cyber-Physical Security, Ali Arsalan

All Dissertations

The electric drive system (EDS) in electric vehicles (EVs) is one of the key safety-critical components. As IoT-enabled communication infrastructure for modern cyber-physical automotive systems continues to evolve, the importance of securing EDS against cyber threats along with physical faults, has become increasingly prominent. Among physical faults, power switches are particularly vulnerable and exhibit the highest susceptibility to open-circuit faults (OCFs). A compromised EDS, whether due to cyber threats or physical issues, can lead to excessive mechanical vibrations, increased thermal stress, fluctuations in electromagnetic torque, and elevated total harmonic distortion. These factors can substantially undermine traction control stability and jeopardize …

Robustness Investigation, Detection, And Defense Of Deep Learning Models Against False Data Injection, Amirhossein Nazeri

All Dissertations

This dissertation addresses the critical challenge of adversarial robustness in deep learning systems, focusing on two fundamental domains: time-series prediction and object detection. As these AI systems become increasingly deployed in safety-critical applications from power grid management to autonomous vehicles their vulnerability to adversarial attacks poses significant risks to infrastructure and human safety.

The first contribution introduces a novel stealthy black-box False Data Injection (FDI) attack specifically designed for quasi-periodic time-series data. Unlike existing attacks that produce easily detectable anomalies, our method generates adversarial perturbations that preserve the underlying periodicity and statistical properties of the data, effectively bypassing traditional anomaly …

Decision Field Theory For Human-Multi-Robot Collaboration: Human-Centric Decision-Making For Multi-Robot Systems, Ryan Mbagna Nanko

All Theses

At first glance, choosing between an apple and an orange appears to be a straightforward matter of personal taste; however, this seemingly simple preference opens a window into the multifaceted world of decision-making, revealing the complex interplay of cognitive processes, psychological, and behavioral-economic principles that guide our choices \cite{bandyopadhyayRoleAffectDecision2013}. By unpacking these nuanced perspectives, we uncover insights that can drive more effective human-robot interaction and collaboration.

Modeling human cognition requires understanding the evolution of choice utility and the influence of emotions. Decision Field Theory (DFT) stands out by capturing the fluctuating nature in human preferences over time, explaining why choices …

Enhancing Autonomous Vehicle Resilience Through Engineering Requirements And Snow-Adaptive Lane Detection, Alexandra Marie Masterson

Masters Theses

This thesis investigates two distinct but interrelated challenges in the development of resilient autonomous vehicle (AV) systems: the formalization of engineering requirements for AV perception subsystems and the enhancement of visual lane detection under snow-covered road conditions. In the first study, field experiments were conducted using a campus-deployed autonomous research vehicle to evaluate the impacts of perception related failures including GPS outages, HD map inconsistencies, and weather interference—on vehicle operation. These findings were used to develop a set of qualitative engineering requirements that promote AV resilience through proactive design. In the second study, a custom snow-focused lane detection dataset was …

Effect Of Using Machine Learning To Improve Active Suspension Control For Vehicle Stability, David A. Butz

Masters Theses

This study demonstrates that it is possible to use road surface classification as a means of informing active suspension systems in order to limit their activity. An approach was taken to improve the response of an active suspension control system by classifying road surfaces in near real time. A control system model was developed to represent a full-body vehicle, and an AI was used to analyze road vibration noise. The model was adapted to allow the AI to select from multiple control signals based on the AI’s analysis of road vibration noise. The objective of the study was to demonstrate …

Algorithms & Design Behind Autonomous Uavs And Ugvs Coordinated System, Aashish Dhakal

Honors Theses

Unmanned Aerial Vehicles (UAVs) and Unmanned Ground Vehicles (UGVs), when coordinated effectively, offer substantial potential for automating large-scale tasks—from search and rescue operations to precision agriculture. However, synchronizing these autonomous systems remains challenging, especially in time-sensitive missions requiring precision. This thesis investigates the design and algorithmic coordination of autonomous UAVs and UGVs, examining both single-vehicle scenarios and multi-agent (swarming) approaches. Using the Robot Operating System (ROS) as a communication backbone, I integrate GPS positioning with computer vision techniques through OpenCV, enabling accurate localization and object detection. During the development phase, I validate my methods using ArduPilot Software-in-the-Loop (SITL) simulations within …

Training Safety Control Filters Using High-Dimensional And Un-Labeled Data, Yuxuan Yang

McKelvey School of Engineering Graduate Student Theses & Dissertations

Synthesizing control policies that preserve the safety of autonomous systems is a challenge that remains to be solved. Towards that goal, control barrier functions (CBFs) have been developed as mathematical constructs that can be used in real-time to correct safety-violating nominal actions to ones which preserve the safety of control systems. However, synthesizing CBFs using correct-by-construction methods has not been scalable. Instead, recent research has proposed data-driven approaches for learning CBFs in the form of neural networks. Two main challenges face such approaches: (1) labeling states as unsafe or safe ones requires the knowledge of the states in the backward …

The Impact Of System Transparency On Perceived System Reliability, Perceived System Usability, And Information Clarity In Self-Driving Car Systems, Uditkumar Nair

Theses and Dissertations

In human-computer interaction (HCI), the development of autonomous vehicle (AV) technology has created new difficulties, especially in building user confidence as well as understanding of system functioning. The effect of system transparency on user- centered outcomes, such as perceived usability, perceived system reliability, and information clarity, is examined in this thesis. In order to evaluate their experiences in both ordinary and high-stakes driving situations, participants engaged with both system- transparent user interfaces (TUIs) and non-transparent user interfaces (NTUIs) across a number of experimental scenarios. In order to assess how well each interface conveyed system logic and actions, the study included …

Analyzing The Resilience Of Infrastructure-Based Vs. Camera-Based Lane Detection In Autonomous Vehicles, Pritesh Yashaswi Patil

Masters Theses

Traditional autonomous vehicle perception subsystems that use on-board sensors have the drawbacks of high computational load and data duplication. Infrastructure-based sensors, which can provide high-quality information without the computational burden and data duplication, are an alternative to traditional autonomous vehicle perception subsystems. However, these technologies are still in the early stages of development and have not been extensively evaluated for lane detection system performance. Therefore, there is a lack of quantitative data on their performance relative to traditional perception methods, especially during hazardous scenarios, such as lane line occlusion, sensor failure, and environmental obstructions. This need is addressed by evaluating …

Techniques For Enabling Advanced Adas Features: Operation In Inclement Weather And Use Of Infrastructure Information, Parth Kadav

Dissertations

Modern vehicles have undergone a transformation with the widespread integration of Advanced Driver Assistance Systems (ADAS) technology becoming the new standard and are set to be mandated by the by the National Highway Traffic Safety Administration (NHTSA) for all passenger vehicles and light trucks. ADAS features have proven to prevent or mitigate crashes by either alerting or assisting the driver. ADAS typically utilizes a forward-facing camera, which comes standard in modern vehicles to provide limited automation features such as Lane Keeping Assist (LKA), and Lane Centering Assist (LCA) to improve driver safety. These systems rely on the assumption that vehicle …

Hyperparameter Tuning For Robust Autonomous Vehicle Vision, Nico D. De Ros

Theses and Dissertations

Classification “flickering,” where the classification of an object changes inconsistently between consecutive video frames, remains a persistent issue in modern object classification algorithms. This problem undermines the reliability of autonomous vision systems and poses significant risks in high-stakes applications such as autonomous vehicles. This thesis explores the use of response surface methodology, a statistical design of experiments technique, to optimize hyperparameters across three object classification pipelines. The first pipeline combines YOLOv8 with SORT to establish a benchmark. The second integrates a Bayesian back-end, while the third employs an exponential smoothing back-end. Hyperparameter tuning was conducted using a two-step process: an …

Advances Towards A Robotic Management Vehicle Suited To Nurse Row Crops To More Efficient Outcomes, Adam Mk Gronewold

Dartmouth College Ph.D Dissertations

Enhancing agricultural production while reducing input costs remains a central challenge in modern row-crop management. Recent advances in computation, imagery, and sensors are enabling more efficient practices across various agricultural domains, and automation technologies are increasingly available to manage tasks central to perennial crop development. Automation in row-crop agriculture, by contrast, lags behind. This thesis explores utilizing small, unmanned ground vehicles to transform row cropping through the implementation of unconventional, in-season management strategies. The first focus of this work considers improvements to nitrogen fertilization using small, autonomous vehicles. An agronomy experiment in corn assessed the effects of gradually applying nitrogen …

Navigating The Future Advancing Autonomous Vehicles Through Robust Target Recognition And Real-Time Avoidance, Mohammed Ahmed Mohammed Hussein

Theses and Dissertations

The problem being tackled by this thesis is a very important one and very relevant to our days and times: it is about making improved target recognition and enhanced real-time response skills in AVs under simulated conditions. Our plan is to put some enhanced sensory capabilities into these vehicles and see if that makes them safer and more reliable. We are using as our base a particular object recognition algorithm (YOLOv7) and a particular simulation environment (CARLA). We utilized the CARLA 0.9.14 simulator on Ubuntu 20.04 as a more stable option than the initially used CARLA 0.9.15 on Ubuntu 22.04, …

Influence Of Time Pressure And Flood Information Type On Flood Alert Effectiveness In Driving, Katherine R. Garcia, Scott Mishler, Jing Chen

Psychology Faculty Publications

Flood alerts are a means of risk communication that alerts the public to potential floods. The purpose of this research was to investigate factors that affected drivers' understanding and actions given a flood presented through a mobile navigation application. Two experiments were conducted to examine the effects of time pressure and type of flood information on drivers' planned actions when faced with potential flooding. Participants were asked about their planned actions given one type of flood information in a driving scenario either with or without time pressure. Our results indicated significant differences in participants' behaviors across the different flood information …

Intelligent Systems For Synergistic Optimization Of Vehicle Dynamics And Energy Consumption In Connected And Automated Vehicles, Aman Poovalappil

Dissertations, Master's Theses and Master's Reports

This dissertation focuses on the development and validation of on-board, real-time estimation algorithms and the investigation of energy-saving strategies for modern light-duty vehicles, including connected and automated vehicles (CAVs). The accurate estimation of key vehicle parameters is critical for enhancing energy efficiency, enabling advanced driver-assistance systems (ADAS), and optimizing vehicle performance and energy efficiency. First, this research introduces a novel real-time algorithm to dynamically learn vehicle mass using readily available sensor data. Based on longitudinal vehicle dynamics, a sensitivity analysis was conducted to identify the conditions under which mass estimation is most robust. The algorithm was extensively validated through on-road …

Development And Verification Of Testing Platform For Torque Vectoring Controller, Nicholas Petersen

Dissertations, Master's Theses and Master's Reports

A foremost concept in the automotive industry in recent years has been that of a vehicle “digital twin”. A digital twin is an accurate simulation of a dynamic system for the use of rapid development. These digital twins have a critical advantage over physical testing, which have dominated vehicle development up to now. As the cost of physical testing continues to rise, simulation can deliver rapid system development in a low-cost format. No simulation environment is a perfect representation of reality, however, and physical testing is still necessary to validate systems for use in the real world. This is especially …

Tl-Convlstm: A Transfer-Learning-Based Convolutional Lstm To Identify And Forecast Traffic In The Nextg Environments, Bikash Chandra Singh, Peter Foytik, Rafael Diaz, Sachin Shetty

School of Cybersecurity Faculty Publications

Forecasting and categorizing cellular traffic flows and their types are essential functions in intelligent network systems to ensure efficient network optimization. The ever-evolving nature of 5G networks results in fluctuations in traffic patterns over time, leading to a phenomenon known as model drift. Consequently, accurately predicting and identifying cellular traffic patterns becomes a complex task. To tackle this challenge, this article introduces an innovative approach called TL-ConvLSTM, which combines transfer learning with convolutional long short-term memory (ConvLSTM) to effectively combat model drift and provide precise forecasting and recognition of cellular traffic within the network. To accomplish this, we initiate the …

Human Perception Of Ai Capabilities At Classifying Perturbed Roadway Signs, Katherine R. Garcia, Jing Chen, Yanru Xiao, Scott Mishler, Cong Wang, Bin Hu

Computer Science Faculty Publications

Artificial Intelligence (AI) is crucial to numerous functions required for driving automation systems, including the computer vision techniques used to detect the roadway environment and make real-time decisions. However, the images used as inputs to the AI system may be maliciously perturbed, or manipulated, causing the AI system to make an incorrect classification. In this study, we examined humans’ perception of the AI’s computer vision capability of classifying various road sign images, including the original images, images with two different types of malicious attacks, and images that are scrambled randomly at the pixel level. Our results showed that participants rated …

Normalizing Images In Various Weather And Lighting Conditions Using Colorpix2pix Generative Adversarial Network, Sanjida Tasnim, Ashif Mahmud Mostafa, Azmain Morshed, Namreen Shaiyaz, Shakib Mahmud Dipto, Saad Aloteibi, Mohammad Ali Moni, Md. Golam Rabiul Alam, Md. Ashraful Alam

Computer Science Faculty Publications

Autonomous vehicles (AVs) are widely regarded as the future of transportation due to their tremendous benefits and user comfort. However, the AVs have been struggling with very crucial challenges, such as achieving reliable accuracy in object detection as well as faster computation required for quick decision-making. In recent years, perception systems in driverless cars have been significantly enhanced, mainly due to advances in deep-learning-based object detection systems. However, these perception systems are still heavily affected by environmental variables, such as changes in illumination, refractive interference, and adverse weather conditions, which may compromise their reliability and safety. This research proposes an …