Efficiently solving global optimization problems remains a pervasive challenge across diverse domains, characterized by complex, high-dimensional search spaces with non-convexity and noise. Most of the approaches in the Bayesian optimization literature have highlighted the computational complexity involved when scaling to high dimensions. Non myopic approximations over a finite horizon has been adopted in recent years by modeling the problem as a partially observable Markov Decision Process (MDP). Another promising direction is the partitioning of the input domain into sub regions facilitating local modeling of the input space. This localized approach helps prioritize regions of interest, which is particularly crucial in high dimensions. However, very few literature exist which leverage agent based modeling of the problem domain along with the aforementioned methodologies. This work explores the synergistic integration of Bayesian Optimization and Reinforcement Learning by proposing a Multi Agent Rollout formulation of the global optimization problem. Multi Agent Bayesian Optimization (MABO) partitions the input domain among a finite set of agents enabling distributed modeling of the input space. In addition to selecting candidate samples from their respective sub regions, these agents also influence each other in partitioning the sub regions. Consequently, a portion of the function is optimized by these agents which prioritize candidate samples that don't undermine exploration in favor of a single step greedy exploitation. This work highlights the efficacy of the algorithm on a range of complex synthetic test functions.

With the explosion of autonomous systems under development, complex simulation models are being tested and relied on far more than in the recent past. This uptick in autonomous systems being modeled then tested magnifies both the advantages and disadvantages of simulation experimentation. An inherent problem in autonomous systems development is when small changes in factor settings result in large changes in a response’s performance. These occurrences look like cliffs in a metamodel’s response surface and are referred to as performance mode boundary regions. These regions represent areas of interest in the autonomous system’s decision-making process. Therefore, performance mode boundary regions are areas of interest for autonomous systems developers.Traditional augmentation methods aid experimenters seeking different objectives, often by improving a certain design property of the factor space (such as variance) or a design’s modeling capabilities. While useful, these augmentation techniques do not target areas of interest that need attention in autonomous systems testing focused on the response. Boundary Explorer Adaptive Sampling Technique, or BEAST, is a set of design augmentation algorithms. The adaptive sampling algorithm targets performance mode boundaries with additional samples. The gap filling augmentation algorithm targets sparsely sampled areas in the factor space. BEAST allows for sampling to adapt to information obtained from pervious iterations of experimentation and target these regions of interest. Exploiting the advantages of simulation model experimentation, BEAST can be used to provide additional iterations of experimentation, providing clarity and high-fidelity in areas of interest along potentially steep gradient regions. The objective of this thesis is to research and present BEAST, then compare BEAST’s algorithms to other design augmentation techniques. Comparisons are made towards traditional methods that are already implemented in SAS Institute’s JMP software, or emerging adaptive sampling techniques, such as Range Adversarial Planning Tool (RAPT). The goal of this objective is to gain a deeper understanding of how BEAST works and where it stands in the design augmentation space for practical applications. With a gained understanding of how BEAST operates and how well BEAST performs, future research recommendations will be presented to improve BEAST’s capabilities.

This thesis is developed in the context of biomanufacturing of modern products that have the following properties: require short design to manufacturing time, they have high variability due to a high desired level of patient personalization, and, as a result, may be manufactured in low volumes. This area at the intersection of therapeutics and biomanufacturing has become increasingly important: (i) a huge push toward the design of new RNA nanoparticles has revolutionized the science of vaccines due to the COVID-19 pandemic; (ii) while the technology to produce personalized cancer medications is available, efficient design and operation of manufacturing systems is not yet agreed upon. In this work, the focus is on operations research methodologies that can support faster design of novel products, specifically RNA; and methods for the enabling of personalization in biomanufacturing, and will specifically look at the problem of cancer therapy manufacturing. Across both areas, methods are presented attempting to embed pre-existing knowledge (e.g., constraints characterizing good molecules, comparison between structures) as well as learn problem structure (e.g., the landscape of the rewards function while synthesizing the control for a single use bioreactor). This thesis produced three key outcomes: (i) ExpertRNA for the prediction of the structure of an RNA molecule given a sequence. RNA structure is fundamental in determining its function. Therefore, having efficient tools for such prediction can make all the difference for a scientist trying to understand optimal molecule configuration. For the first time, the algorithm allows expert evaluation in the loop to judge the partial predictions that the tool produces; (ii) BioMAN, a discrete event simulation tool for the study of single-use biomanufacturing of personalized cancer therapies. The discrete event simulation engine was designed tailored to handle the efficient scheduling of many parallel events which is cause by the presence of single use resources. This is the first simulator of this type for individual therapies; (iii) Part-MCTS, a novel sequential decision-making algorithm to support the control of single use systems. This tool integrates for the first-time simulation, monte-carlo tree search and optimal computing budget allocation for managing the computational effort.

Generative Adversarial Networks (GANs) have emerged as a powerful framework for generating realistic and high-quality data. In the original ``vanilla'' GAN formulation, two models -- the generator and discriminator -- are engaged in a min-max game and optimize the same value function. Despite offering an intuitive approach, vanilla GANs often face stability challenges such as vanishing gradients and mode collapse. Addressing these common failures, recent work has proposed the use of tunable classification losses in place of traditional value functions. Although parameterized robust loss families, e.g. $\alpha$-loss, have shown promising characteristics as value functions, this thesis argues that the generator and discriminator require separate objective functions to achieve their different goals. As a result, this thesis introduces the $(\alpha_{D}, \alpha_{G})$-GAN, a parameterized class of dual-objective GANs, as an alternative approach to the standard vanilla GAN. The $(\alpha_{D}, \alpha_{G})$-GAN formulation, inspired by $\alpha$-loss, allows practitioners to tune the parameters $(\alpha_{D}, \alpha_{G}) \in [0,\infty)^{2}$ to provide a more stable training process. The objectives for the generator and discriminator in $(\alpha_{D}, \alpha_{G})$-GAN are derived, and the advantages of using these objectives are investigated. In particular, the optimization trajectory of the generator is found to be influenced by the choice of $\alpha_{D}$ and $\alpha_{G}$. Empirical evidence is presented through experiments conducted on various datasets, including the 2D Gaussian Mixture Ring, Celeb-A image dataset, and LSUN Classroom image dataset. Performance metrics such as mode coverage and Fréchet Inception Distance (FID) are used to evaluate the effectiveness of the $(\alpha_{D}, \alpha_{G})$-GAN compared to the vanilla GAN and state-of-the-art Least Squares GAN (LSGAN). The experimental results demonstrate that tuning $\alpha_{D} < 1$ leads to improved stability, robustness to hyperparameter choice, and competitive performance compared to LSGAN.

Efforts to enhance the quality of life and promote better health have led to improved water quality standards. Adequate daily fluid intake, primarily from tap water, is crucial for human health. By improving drinking water quality, negative health effects associated with consuming inadequate water can be mitigated. Although the United States Environmental Protection Agency (EPA) sets and enforces federal water quality limits at water treatment plants, water quality reaching end users degrades during the water delivery process, emphasizing the need for proactive control systems in buildings to ensure safe drinking water.Future commercial and institutional buildings are anticipated to feature real-time water quality sensors, automated flushing and filtration systems, temperature control devices, and chemical boosters. Integrating these technologies with a reliable water quality control system that optimizes the use of chemical additives, filtration, flushing, and temperature adjustments ensures users consistently have access to water of adequate quality. Additionally, existing buildings can be retrofitted with these technologies at a reasonable cost, guaranteeing user safety. In the absence of smart buildings with the required technology, Chapter 2 describes developing an EPANET-MSX (a multi-species extension of EPA’s water simulation tool) model for a typical 5-story building. Chapter 3 involves creating accurate nonlinear approximation models of EPANET-MSX’s complex fluid dynamics and chemical reactions and developing an open-loop water quality control system that can regulate the water quality based on the approximated state of water quality. To address potential sudden changes in water quality, improve predictions, and reduce the gap between approximated and true state of water quality, a feedback control loop is developed in Chapter 4. Lastly, this dissertation includes the development of a reinforcement learning (RL) based water quality control system for cases where the approximation models prove inadequate and cause instability during implementation with a real building water network. The RL-based control system can be implemented in various buildings without the need to develop new hydraulic models and can handle the stochastic nature of water demand, ensuring the proactive control system’s effectiveness in maintaining water quality within safe limits for consumption.

Photolithography is among the key phases in chip manufacturing. It is also among the most expensive with manufacturing equipment valued at the hundreds of millions of dollars. It is paramount that the process is run efficiently, guaranteeing high resource utilization and low product cycle times. A key element in the operation of a photolithography system is the effective management of the reticles that are responsible for the imprinting of the circuit path on the wafers. Managing reticles means determining which are appropriate to mount on the very expensive scanners as a function of the product types being released to the system. Given the importance of the problem, several heuristic policies have been developed in the industry practice in an attempt to guarantee that the expensive tools are never idle. However, such policies have difficulties reacting to unforeseen events (e.g., unplanned failures, unavailability of reticles). On the other hand, the technological advance of the semiconductor industry in sensing at system and process level should be harnessed to improve on these “expert policies”. In this thesis, a system for the real time reticle management is developed that not only is able to retrieve information from the real system, but also can embed commonly used policies to improve upon them. A new digital twin for the photolithography process is developed that efficiently and accurately predicts the system performance thus enabling predictions for the future behaviors as a function of possible decisions. The results demonstrate the validity of the developed model, and the feasibility of the overall approach demonstrating a statistically significant improvement of performance as compared to the current policy.

The COVID-19 outbreak that started in 2020, brought the world to its knees and is still a menace after three years. Over eighty-five million cases and over a million deaths have occurred due to COVID-19 during that time in the United States alone. A great deal of research has gone into making epidemic models to show the impact of the virus by plotting the cases, deaths, and hospitalization due to COVID-19. However, there is very less research that has anything to do with mapping different variants of COVID-19. SARS-CoV-2, the virus that causes COVID-19, constantly mutates and multiple variants have emerged over time. The major variants include Beta, Gamma, Delta and the recent one, Omicron. The purpose of the research done in this thesis is to modify one of the epidemic models i.e., the Spatially Informed Rapid Testing for Epidemic Model (SIRTEM), in such a way that various variants of the virus will be modelled at the same time. The model will be assessed by adding the Omicron and the Delta variants and in doing so, the effects of different variants can be studied by looking at the positive cases, hospitalizations, and deaths from both the variants for the Arizona Population. The focus will be to find the best infection rate and testing rate by using Random numbers so that the published positive cases and the positive cases derived from the model have the least mean square error.

In recent years, the development of Control Barrier Functions (CBF) has allowed safety guarantees to be placed on nonlinear control affine systems. While powerful as a mathematical tool, CBF implementations on systems with high relative degree constraints can become too computationally intensive for real-time control. Such deployments typically rely on the analysis of a system's symbolic equations of motion, leading to large, platform-specific control programs that do not generalize well. To address this, a more generalized framework is needed. This thesis provides a formulation for second-order CBFs for rigid open kinematic chains. An algorithm for numerically computing the safe control input of a CBF is then introduced based on this formulation. It is shown that this algorithm can be used on a broad category of systems, with specific examples shown for convoy platooning, drone obstacle avoidance, and robotic arms with large degrees of freedom. These examples show up to three-times performance improvements in computation time as well as 2-3 orders of magnitude in the reduction in program size.

The notion of the safety of a system when placed in an environment with humans and other machines has been one of the primary concerns of practitioners while deploying any cyber-physical system (CPS). Such systems, also called safety-critical systems, need to be exhaustively tested for erroneous behavior. This generates the need for coming up with algorithms that can help ascertain the behavior and safety of the system by generating tests for the system where they are likely to falsify. In this work, three algorithms have been presented that aim at finding falsifying behaviors in cyber-physical Systems. PART-X intelligently partitions while sampling the input space to provide probabilistic point and region estimates of falsification. PYSOAR-C and LS-EMIBO aims at finding falsifying behaviors in gray-box systems when some information about the system is available. Specifically, PYSOAR-C aims to find falsification while maximizing coverage using a two-phase optimization process, while LS-EMIBO aims at exploiting the structure of a requirement to find falsifications with lower computational cost compared to the state-of-the-art. This work also shows the efficacy of the algorithms on a wide range of complex cyber-physical systems. The algorithms presented in this thesis are available as python toolboxes.

Automated driving systems (ADS) have come a long way since their inception. It is clear that these systems rely heavily on stochastic deep learning techniques for perception, planning, and prediction, as it is impossible to construct every possible driving scenario to generate driving policies. Moreover, these systems need to be trained and validated extensively on typical and abnormal driving situations before they can be trusted with human life. However, most publicly available driving datasets only consist of typical driving behaviors. On the other hand, there is a plethora of videos available on the internet that capture abnormal driving scenarios, but they are unusable for ADS training or testing as they lack important information such as camera calibration parameters, and annotated vehicle trajectories. This thesis proposes a new toolbox, DeepCrashTest-V2, that is capable of reconstructing high-quality simulations from monocular dashcam videos found on the internet. The toolbox not only estimates the crucial parameters such as camera calibration, ego-motion, and surrounding road user trajectories but also creates a virtual world in Car Learning to Act (CARLA) using data from OpenStreetMaps to simulate the estimated trajectories. The toolbox is open-source and is made available in the form of a python package on GitHub at https://github.com/C-Aniruddh/deepcrashtest_v2.