Computer Engineering Commons^™

Stretch Web Teleoperation Keyboard Final Report, Aaron Chou, Francisco Irazaba

Computer Engineering

This project added keyboard controls to the Hello Robot Stretch Web Teleop interface. The goal was to make the robot easier to control from a web browser without needing a gamepad or separate terminal-based keyboard program. The new interface allows users to control different parts of the robot with customizable key bindings.

Learning Adaptive Control For Safe Collaborative Autonomous Driving, Fabian Alexis Hernandez

Theses and Dissertations

Connected autonomous vehicles improve urban driving through collaborative perception via Vehicle-to-Everything (V2X) communication. Frameworks such as V2Xverse leverage this collaboration for planning and perception, yet their controllers rely on fixed parameters that cannot adapt to varying traffic. Control Barrier Functions (CBFs) enforce safety by constraining actions within a safe set, but a fixed barrier gain imposes a single operating point: conservative settings reduce throughput while permissive settings under-react to hazards.

This research proposes an adaptive CBF framework that learns state-dependent, class-specific barrier gains via constrained Reinforcement Learning (RL). A compact policy outputs separate gains for vehicles, pedestrians, and bicycles, parameterizing …

Safe Control Design For Quadruped Locomotion In Unstructured Environments Using Linear Transfer Operators, Sriram Sundar Krishnamoorthy Shankara Narayanan

All Dissertations

Deploying quadruped robots in unstructured, obstacle-rich environments requires control and planning methods that remain safe and reliable despite complex terrain geometry, limited sensing, and inevitable modeling errors. This thesis develops operator-theoretic tools for safe control design of robotic systems using linear transfer operators, with a focus on quadruped locomotion in unstructured environments. The central goal is to develop a unified operator-theoretic framework for safe control design based on the Perron–Frobenius (P–F) and Koopman operators. In particular, the thesis leverages \emph{density functions} to develop safe navigation frameworks in the dual space of densities. In the operator-theoretic perspective, the P–F operator governs …

A Low-Cost Motion Classification System For A Stuffed Animal Using An Imu And Machine Learning, Rachel N. Guynes

Honors Theses

One of the many fields that has seen the integration of robots is therapy. Zoomorphic robots (ZR) are designed to look and behave like animals to assist in Animal Assisted Therapy (AAT) practices. Studies show that ZRs can provide benefits similar to working with an actual animal; however, their high cost limits their accessibility. This thesis documents the process of building a real-time, low-cost motion classification system that can be attached to a stuffed animal to make it more interactive. Using a Random Forest (RF) classifier, the system identifies movements with approximately 81.67% accuracy.

Approach To Physics Education Using Local Ai With Rag For Open Educational Materials Generation, Dmitriy Beznosko

All Things Open

The new tool that starts to enter all parts of our life is AI – and it enters education as well. There are two standing large concerns with using AI for education – the safety of students’ data and the AI missing specific knowledge about the given class. The approach of using the Retrieval Augmented Generation (RAG) provides the user data to the locally run LLM model (using Ollama framework, a free and open-source tool that allows you to run large language models locally on your system) as a context for the generation of the OER materials. As this AI …

Multiple-Valued Quantum Automata For Robotics, Yuchen Huang

Dissertations and Theses

This dissertation introduces a new type of quantum automata, their encoding and circuit realization. I concentrate on possible applications in robotics. Several methods and application of quantum automata and quantum circuit-based controllers for elementary robotic systems, with a focus on humanoid robot motion, emotion, and behavior generation are illustrated in detail. The research introduces several novel methodologies that bridge quantum computing principles with robotic control, aiming to overcome the limitations of classical deterministic and probabilistic approaches.

The dissertation first presents a quantum-circuit-based framework for generating non-repetitive and expressive (e)motions in a humanoid robot actor, using superposition and entanglement to produce …

Ultragps: A Low-Cost, Open-Source Ultrasonic Positioning System, Scott Roelker Murillo, Nnamdi Jesse Onwuzurike

Posters - 2026

We want to raise the bar in high school robotics. In Texas, and likely in many other states as well, high school robotics has reached a roadblock when it comes to autonomous navigation. In many competitions, the autonomous portion sees few, teams successfully completing tasks that require positioning and guidance. In modern robotics, it is no longer sufficient for a robot merely be “remote controlled.” They need to be able to navigate independently and adapt to the environment around them. To achieve this goal a positioning system is needed to develop the foundational algorithms for autonomous controls. However, these systems …

Behavioral-Centric Team Evaluation Via Consistent Rewards, Clement Kudakwashe Nyanhongo

Dartmouth College Ph.D Dissertations

Across human domains ranging from sports to business and organizational settings, complex tasks are often solved by teams rather than individuals, leveraging benefits such as interaction, mutual support, complementary skills, cohesion, and task allocation. Evaluating team effectiveness, however, is inherently challenging due to the subjectivity of many existing techniques and the limitations of outcome-driven metrics that primarily focus on performance scores while overlooking the team processes that generated the scores. To address these challenges, this dissertation proposes a behavioral-centric, end-to-end framework for team evaluation grounded in reward functions that model sequential team behavior. Reward functions offer compact and interpretable representations …

Tuning And Performance Of Pid Controlled Low Complexity Systems, Timothy Evans

Honors Theses

Proportional integral derivative (PID) controllers are used for precise position and orientation control in systems such as autonomous underwater vehicles (AUVs). This project supports the University of Southern Mississippi’s (USM) Robotics Club’s RoboSub AUV effort by developing, troubleshooting, and manually tuning PID controllers to characterize tracking performance and settling time across systems of increasing complexity. Initially, the project hypothesized that tracking performance would be reduced and settling times would increase as system complexity advanced from one degree-of-freedom (DOF) to two DOF. However, prior research was found that suggests that for small disturbances around an equilibrium state, separate PID-controlled DOFs can …

Using Ai To Predict Energy Expenditure In Lower Limb Prosthesis Users, Nelly Diaz, Siem Hadish

Posters - 2026

• Computer vision has evolved from simple image classification and object detection to analyzing human motion and biomechanics (1). • CNN’s are usually focused on image classification, but, in this case, we are not asking the model if a person is walking. • Many real-world problems require regression: Predicting a continuous number like energy expenditure of walking is a complex task. • It is essential for Prosthetists to understand energy expenditure of their prosthetic patients (2). • An amputee may use 20-30% more energy to walk. • In this project, we developed an AI model to analyze human motion and …

Optimizing Auv Perception For Competitive Underwater Robotics: Analyzing Performance And Simplicity Of Machine Vision Hardware, Joseph King

Honors Theses

Underwater robotics is a growing field with many practical applications, such as pipeline and offshore structure monitoring, deep sea mining, mine reconnaissance/removal, and marine environmental monitoring. USM’s Robotics Club will participate in the international RoboSub competition, where student-led teams build autonomous underwater vehicles (AUVs) that perform a variety of tasks within a pool requiring camera-based object detection. This project analyzes affordable hardware and software options for providing machine vision to USM’s future RoboSub AUV. The performance of an ESP32-CAM microcontroller, Raspberry Pi 5, and Jetson Orin Nano single-board computers running FOMO and YOLO object detection models was compared. These models …

A Pretraining-Based Framework For On-Device Training Of Imu-Based Locomotion Mode Detection For Wearable Active Exoskeletons, Muhammad Tahir Khan

LSU Master's Theses

Active exoskeletons are being developed to support human movement in physically demanding industries such as construction. For these systems to work effectively, they must be able to correctly identify the user’s current activity. This process is known as locomotion mode detection and plays an important role in selecting the appropriate control parameters for exoskeletons. Many existing approaches use inertial measurement units (IMUs) to recognize these activities and have shown strong performance. However, most of these methods depend on large amounts of labeled data collected under specific conditions. As a result, they often do not perform well when applied to new …

Ai-Scm Cmm: A Capability Maturity Model For Artificial Intelligence Integration In Supply Chain Management, Lordt Becklines, Omar F. El-Gayar, Patti Brooks, Insu Park

Annual Research Symposium

Artificial intelligence is increasingly deployed in supply chain management, yet many organizations struggle to align adoption efforts with process readiness, data quality, governance, and workforce capabilities, and they still lack validated supply chain specific roadmap for assessing readiness, sequencing investments, and reducing implementation risk. This study develops and evaluates a Capability Maturity Model for Artificial Intelligence Integration in Supply Chain Management to address that gap. Using a design science research approach, the study synthesizes prior literature and practitioner knowledge to define maturity dimensions, capability indicators, and staged progression levels for AI integration in supply chain contexts. The artifact and assessment …

Identification Of Thruster Faults In Underwater Vehicles By Using Custom Encodings In Spiking Neural Networks, Donovan Gegg

LSU Master's Theses

Autonomous Underwater Vehicles (AUVs) are untethered robotic platforms used for tasks such as seafloor mapping, infrastructure inspection, and environmental monitoring. Recent technological advances have produced smaller, more affordable platforms, broadening access to research teams and small companies alike. This miniaturization comes at the cost of them handling drawbacks associated with a more compact machine such as reduced battery capacity as well as limited processing and sensing capabilities. These constraints make small-sized marine vehicle’s reliability critical as they can cause malfunctions, making the loss of a vehicle more likely. Actuator faults are particularly consequential as unintended and unstable control in an …

Evaluating Regularized Logistic Regression And K-Nn On Mnist Under Increasing Random Missingness, Daniel Markwei

Data Science and Data Mining

This paper investigates the effect of random missingness on the performance of regularized multinomial logistic regression and the k-nearest neighbors (k-NN) classifier for handwritten digit recognition on the MNIST dataset. In particular, we study L1-regularized (LASSO) logistic regression and L2-regularized (Ridge) logistic regression alongside k-NN. Varying percentages of random missingness were introduced into the original dataset, and each model was evaluated in terms of its classification performance. The results show that random missingness degrades the performance of all three classifiers. Overall, k-NN consistently achieves higher accuracy than both L1- and L2-regularized logistic regression across all missingness levels; however, its performance …

A Capability Maturity Model For Artificial Intelligence Integration In Supply Chain Management, Lordt Becklines

Dissertations

Artificial Intelligence (AI) is transforming Supply Chain Management (SCM), yet many organizations struggle to assess their readiness for AI adoption and to understand how AI capabilities develop across maturity stages. This dissertation addresses this gap by developing a Capability Maturity Model (CMM) for AI integration in SCM, grounded in Organizational Information Processing Theory (OIPT), the Resource-Based View, and related capability frameworks. The model provides a structured approach for evaluating an organization's information-processing requirements, resource configurations, and alignment needed for effective AI-enabled supply chain operations.

Using a design science research approach, the AI-SCM CMM and its associated assessment instrument were derived …

Digital Replica For Trustworthy Cooperative Autonomous Vehicles, Hady Farahat

Theses and Dissertations

Trust in an automated system can be defined as confidence in a vehicle's reliability, safety, and predictability, which is essential for the acceptance and widespread adoption of fully autonomous vehicles (FAVs); without it, users might disengage from using autonomous vehicles or reject the technology altogether. Most of the previous research has focused on trust from an ego vehicle perspective.

However, next-generation vehicles are becoming more autonomous and connected, relying on vehicle-to-vehicle technology and vehicle-to-infrastructure technology with no human intervention. Hence, trust becomes more complex and fragile as multiple agents interact with each other, and it might become harder to establish …

Human-Machine Communication: Complete Volume. Volume 12

Human-Machine Communication

This is the complete volume of HMC Volume 12.

Whole Earth Machines: Human-Machine Communication For A Green Transition, Klaus Bruhn Jensen

Human-Machine Communication

The climate crisis of the 21st century represents an existential risk to humanity and biodiversity, posing essential questions of how communication may serve to coordinate mitigation of and adaptation to climate change. One recent response has been massive investments by governments and corporations in systems providing feedback on the state of Earth— Whole Earth Machines (WEMs). For human-machine communication (HMC) studies, WEMs invite sustained engagement with communication infrastructures as a key constituent of research agendas, beyond the interface encounters at the center of many HMC studies to date. The article presents a conceptualization and operationalization of WEMs as critical infrastructures …

Robotic Air Hockey Table, William Forcey, Andrew Piunno, Kaden Carpenter, Xander Zavatchen

Williams Honors College, Honors Research Projects

Air hockey, a popular arcade game, is traditionally designed for two players. This limits the game’s accessibility for individuals who wish to practice or enjoy it as a single player. To solve this problem, a robotic system was implemented to play air hockey against a human player. The speed and acceleration of the puck and mallet were measured from a game played between humans to inform the required movement capabilities of the robot. The robotic opponent implemented observes the location of the puck on the table using a camera and predicts where it will be in the future. A Cartesian …

A Web-Based Wizard-Of-Oz Platform For Collaborative And Reproducible Human-Robot Interaction Research, Sean O'Connor

Honors Theses

The Wizard-of-Oz (WoZ) technique is widely used in Human-Robot Interaction (HRI) research, but two persistent problems limit its effectiveness: existing tools impose technical barriers that exclude non-engineering domain experts (the Accessibility Problem), and the fragmented landscape of robot-specific implementations makes interaction scripts difficult to port across platforms (the Reproducibility Problem- concerning execution consistency and portability, not third-party replication). Through a literature review, I identified three design principles to address both: a hierarchical specification model, an event-driven execution model, and a plugin architecture that decouples experiment logic from robot-specific implementations. I realized these principles in HRIStudio, an open-source, web-based platform providing …

Proactive Safety Reasoning In Human-Robot Collaboration In Disassembly Through Llm-Augmented Stpa And Fmea, Morteza Jalali Alenjareghi, Fardin Ghorbani, Samira Keivanpour, Yuvin Adnarain Chinniah, Sabrina Jocelyn

Études primaires

Disassembly tasks in human–robot collaboration (HRC) environments present safety challenges due to hazardous materials, control system variability, and physically demanding operator tasks. To address these challenges, we propose an AI-augmented risk assessment framework integrating System-Theoretic Process Analysis (STPA) and Failure Mode and Effects Analysis (FMEA). This framework is implemented in four configurations: Term Frequency– Inverse Document Frequency (TF-IDF), Fine-tuned Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and RAG with a structured Knowledge Graph (KG) built from safety standards. The system supports real-time, standards-compliant safety reasoning by generating interpretable, context-specific recommendations. We evaluate these configurations across GPT-3.5 TURBO, GPT-4o, GPT-4.1, and …

Learning-Enabled Methods For Optimal, Constrained, And Fault-Tolerant Robot Motion Planning, Charles L. Clark

Theses and Dissertations--Electrical and Computer Engineering

Safe and efficient motion planning is a core requirement for robots operating in complex real-world environments, yet traditional model-based approaches struggle to simultaneously achieve computational efficiency, solution optimality, and the ability to handle complex constraints and potential hardware failures. This dissertation investigates how neural networks, as general purpose function approximators, can be leveraged in both traditional and novel ways to overcome these limitations and advance beyond what purely model-based methods can offer. Three distinct contributions are presented. First, a new motion planner is developed that uses ReLU neural networks to decompose the configuration space into linear cost regions, enabling existing …

End-To-End Development And Experimental Validation Of A 1/10-Scale Autonomous Vehicle, Rikkin Pankaj Panchal

Electrical Engineering Theses

Autonomous vehicle development demands vast resources, making scaled down platforms a critical alternative for solving core algorithmic challenges. The primary contribution of this thesis is the end to end development and validation of a complete real time autonomous driving pipeline deployed on a one tenth scale vehicle. To streamline platform development, an AI assisted annotation framework automates dataset generation, significantly reducing manual labor while improving training data quality. The system perception stack features a reinforcement learning guided online multi camera calibration framework that enables adaptive surround view stitching without the need for offline recalibration. This is paired with robust lane …

Heterogeneous Robots Cooperation Via Multi-Agent Reinforcement Learning, Rehab Uddin Shawon

Graduate Theses/Dissertations

Enabling heterogeneous robots with diverse capabilities, roles, and task responsibilities to coordinate effectively in complex, dynamic environments remains a fundamental challenge in autonomous multi-robot systems. Multi-Agent Reinforcement Learning (MARL) provides a promising framework for decentralized cooperation. However, most existing MARL approaches assume homogeneous agents or fixed single-task settings and suffer significant performance degradation as the number of robot and task types increases. This thesis presents a scalable shared-policy MARL framework that allows heterogeneous robots to learn specialized behaviors for individual, sequential, and collaborative tasks involving temporal and spatial dependencies through a single neural policy. I first embed robot identity directly …

Cross-Layer Supervisory Control For Low-Altitude Uav Swarm Networks, Nitin Singh Rathore

Computer Science and Engineering Theses

Low-altitude unmanned aerial vehicle (UAV) swarms are increasingly used in applications such as aerial sensing, disaster response, and communication support, where reliable operation under dynamic and uncertain conditions is essential. In these environments, performance degradation arises from multiple sources, including external disturbances, sensing uncertainty, and communication impairments. Although these effects originate from different layers of the system, such as dynamics, observation, and networking, they often manifest as similar tracking or coordination errors. Conventional control approaches, which rely primarily on error-driven feedback, do not explicitly account for the underlying cause of these deviations, limiting their effectiveness in multi-agent settings. This thesis …

Multi-Level Energy Optimization For Connected And Automated Vehicles: From Cooperative Multi-Vehicle Control To Individual Powertrain Management, Pruthwiraj Santhosh

Dissertations, Master's Theses and Master's Reports

The transportation sector currently accounts for nearly 30% of global energy consumption, necessitating urgent advancements in vehicle efficiency to meet Net Zero targets. Leveraging connectivity and automation, this dissertation proposes and validates methodologies to reduce the energy consumption of light-duty vehicles at both fleet and individual levels.

First, a validation framework is developed to bridge the “simulation-to-real world” gap in Cooperative Automated Vehicle (CAV) research. Moving beyond virtual simulations, the study establishes a methodology for physically validating centralized control architectures via a custom Cellular V2X network. By synchronizing vehicle-powertrain models with physical test vehicles, the framework successfully orchestrates complex arterial …

The Excess Path Length Distribution: A Stochastic Model For Sample-Based Path Planners, Chaz B. Cornwall

Dissertations, Master's Theses and Master's Reports

Through random sampling, sample-based path planners enable autonomous agents to quickly find paths without human intervention. However, due to the paths' randomness, sample-based path planners currently require additional verification, partially nullifying agents' ability to act autonomously. I set out to characterize this uncertainty so humans know what to expect from these path planners and know how to alter the path planner to desired specifications. To ensure the results are theoretical as well as practical, I first create a stochastic model of path length uncertainty using the trade-off between sampling time and optimality. By leveraging this model, my proposed algorithm reduces …

Using Automotive Lidar To Reduce The Energy Consumption Of An Ego Autonomous Vehicle, Logan P. Schexnaydre

Dissertations, Master's Theses and Master's Reports

There is significant potential to reduce the energy consumption of the transportation sector through autonomous vehicles. Prior work on autonomous vehicle energy efficiency focuses on the whole system or the control subsystem. Yet, the sensing and processing components, which have direct and indirect effects on net energy use, are less explored. This dissertation fills this gap by modeling and evaluating these effects for lidar sensors, which provide high-resolution spatial data at the cost of high power and processing demands. I apply lidar to the energy-saving tasks of automated vehicle following and road surface profiling. For automated vehicle following, I model …

Making Robotic Reinforcement Learning More Efficient: Analyzing The Serl Framework, Faris Jugovic, Cleiver Ruiz-Martinez, Ryan Vander Stelt

Student Scholar Symposium

Teaching robots through reinforcement learning (RL) has made great progress, but real-world training is still difficult. Robots need lots of practice to learn, rewards can be hard to define, and resetting the environment after each attempt is often a challenge. The Sample-Efficient Robotic Reinforcement Learning (SERL) framework helps solve these issues by offering a ready-to-use, open-source software package that makes RL more practical for real-world robotics.

This project explores SERL and how it improves robotic RL by making learning faster and more efficient. SERL includes smarter ways to reuse training data, automatic methods for understanding rewards from images, and a …