Navigation, Guidance, Control and Dynamics Commons^™

Application Of Reinforcement Learning To Precision Aerial Delivery System Control In Adverse Wind Conditions, Radman Zarbock

The Journal of Purdue Undergraduate Research

Precision aerial delivery systems (PADS) are a subset of airdropped parachute-leveraging package delivery systems that use autonomous guidance, navigation, and control (GNC) to reach targets with high degrees of accuracy. This technology emerged in the 1990s, and strides have been made since to improve the reliability of traditional physics-based controllers that guide PADS. However, these algorithms still struggle to deliver acceptable performance results when PADS are subjected to austere operating environments, such as those with unpredictable wind. Building on a foundational study in 2022 that used artificial intelligence (AI) and machine learning to improve PADS GNC performance, this study aims …

Amp: Single-Shot Ultra-Wide Fisheye-To-Cubemap Pnp Pose Estimation, Ryan M. Raettig, Richard R. Nyquist, Scott L. Nykl, Clark N. Taylor, Christine M. Schubert Kabban

Faculty Publications

Estimating the position and orientation of a rigid object from an image is critical for situational awareness in robotics and autonomous systems. This study explores relative pose estimation using an ultra-wide fisheye camera for unmanned aircraft inspection vehicles. Ultra-wide fisheye lenses introduce radial distortion and capture features beyond the rectilinear image plane, rendering rectilinear Perspective-n-Point (PnP) algorithms inadequate. Designing a bespoke ultra-wide fisheye localization algorithm requires consideration of both the feature detection method and the pose estimator itself. This study proposes a novel method that combines (1) a fisheye-to-cubemap reprojection, (2) a You Only Look Once (YOLO) convolutional neural network …

Graph Based Planning With Guarantees, Trazon Tyrik Jimerson

Mechanical Engineering ETDs

This thesis presents two graph-based methods with formal guarantees for motion planning and routing. First, the invariant-set motion planner (ISMP), which uses constraint admissible positive invariant (CAPI) sets of closed-loop dynamics, is adapted for spacecraft attitude planning to avoid moving keep-out zones. Contributions include time bounds for maneuvers via exponential stability, a single-stage reachability graph from one-step backward reachable CAPI sets, and its multi-stage expansion to certify node safety over time. Simulations verify safe attitude control with moving obstacles. Second, we formulate a convex optimization problem over a network for evacuation planning with operational constraints such as helicopter capacity and …

Parameter Informed Reinforcement Learning For Vehicle System Identification, Nathan Schaff

Doctoral Dissertations and Master's Theses

Accurate system identification is essential for modeling and controlling vehicle dynamics. This dissertation explores the application of Parameter Informed Reinforcement Learning (PIRL) as a novel approach to system identification (SYSID). PIRL integrates prior system knowledge, such as physical parameters, into reinforcement learning (RL) frameworks to improve estimation accuracy. The study begins with an overview of traditional SYSID methods and then introduces PIRL as a modification of standard RL. The research applies PIRL to short-period aircraft dynamics, demonstrating its effectiveness in both offline and online learning frameworks. The dissertation then further explores PIRL’s utility in an indirect model reference adaptive control …

Understanding Policy Transfer Under Decomposition And Coordination: Sequential Reinforcement Learning With Relaxation-Based Feasibility Control, Aannand Lal

All Theses

This thesis investigates how decomposition and coordination (D&C) choices influence exploration, learning, and transfer in reinforcement learning (RL) based design frameworks. A unified methodology is developed to evaluate generality under decomposition and to demonstrate sequential coordination on a representative physical task. The generality study holds the underlying physics constant while varying problem presentation - specifically scalarization weights, objective orientations, and feasibility handling. A train-evaluate matrix is constructed in which each trained policy is assessed across all alternative decompositions. Set-based diagnostics quantify generality through exact-match identity, Jaccard similarity of distinct feasible states, total feasible coverage, and Pareto-front quality. Results show that …

Development And Test Of An Automatic Mass Balancing System For Cal Poly's Spacecraft Attitude Dynamics Simulator, Cameron B. Zorio

Master's Theses

The Cal Poly Spacecraft Attitude Dynamics Simulator (SADS) is an ongoing project to develop an air-bearing platform capable of recreating on-orbit rotational dynamics with near frictionless and torque-free rotations. However, any offset between the platform's center of rotation and its center of mass will introduce a torque due to gravity.

This thesis presents the design, implementation, and experimental evaluation of a low-cost, automatic mass balancing system for the SADS to address this challenge. A new modular sliding mass system was developed that overcomes issues faced in previous iterations of the SADS, providing real-time positional control of the masses and a …

Insights On Ai-Supported Uncrewed And Autonomous Systems Education, Brent A. Terwilliger Ph. D, John Faraca

Publications

Artificial Intelligence (AI) related technology is reshaping the educational experience in programs focused on uncrewed and autonomous systems, aviation, robotics, and aerospace, with growing implications for workforce readiness and cross-sector innovation. Early survey data, capturing student, educator, and employer perspectives, reveals that AI-supported tools are notably changing student engagement, communication, and skills development. Initial indications underscores the importance of AI proficiency and technological familiarity in hiring and workforce development, particularly in technical and operational roles. Key areas of focus include the use of AI to strengthen outreach and interactivity; enrich instruction through intelligent simulations; inform curricular improvements using data analytics; …

Adaptive Control For Spacecraft With Flexible Appendages With Unknown Parameters, Nicolo Woodward

Doctoral Dissertations and Master's Theses

Flexible spacecraft pose several challenges in control design due to the uncertain dynamical model and the underactuated nature of these systems. Adaptive and robust controllers are the common choice for these systems to either meet operational requirements like attitude pointing or to suppress vibrations. However, these controllers add complexity in the design of onboard Attitude Determination and Control Systems (ADCS) and the Reaction Control Systems (RCS) for spacecraft maneuvering. The objective of this research is to control a system that undergoes unpredictable and unknown disturbances through onboard derivation of an equivalent reduced order model designed around mounted sensors. The proposed …

Autonomous Landing Of An Unmanned Aerial Vehicle On An Unmanned Surface Vessel Using Model Predictive Control With An Adaptive-Covariance Extended Kalman Filter, Jorge Estupinan

Doctoral Dissertations and Master's Theses

This thesis presents the development of vision-based estimation and model predictive control (MPC) strategies to enable an Unmanned Aerial Vehicle (UAV) to land autonomously on an Unmanned Surface Vessel (USV) subjected to wave-induced motion. An innovative Adaptive-Covariance Extended Kalman Filter (AEKF) implementation was developed for the estimation of the 6 degree-of-freedom USV states using GPS and vision-based measurements of AprilTag markers on the USV landing platform. The AEKF employs an uncontrolled 6 degree-of-freedom nonlinear model augmented with second-order harmonic wave-induced motion dynamics. The AEKF implements two correction techniques: an adaptive covariance adjustment and an artificial covariance inflation regulated by a …

Unresolved Image Simulation For Space Situational Awareness Applications, Fox Coniglario

Doctoral Dissertations and Master's Theses

The knowledge of what lies in orbit around Earth is at best a guess. Decades of spaceflight, debris buildup, and vehicle collisions have contributed to a large number of objects that are simply not able to be catalogued. Ongoing efforts to catalog debris in orbit have reached limits by conventional measures and as such, research is active in the field of in-orbit space situational awareness. This thesis intends to help fill a hole in the development of such orbital platforms by assisting the development of image processing software pipelines though the simulation of unresolved space imagery. The simulation uses accurate …

Dissociation Of Subjective And Objective Measures Of Trust In Vehicle Automation: A Driving Simulator Study, Samuel Petkac, Tetsuya Sato, Kun Xie, Yusuke Yamani

Psychology Faculty Publications

Trust is a crucial factor that influences human-automation interaction in surface transportation. Previous research indicates that participants tend to display higher levels of subjective trust toward lower-level automated systems compared to high-level automated systems. However, administering subjective trust measures via questionnaires can interfere with primary task performance, limiting researchers' ability to measure trust continuously in a real-world manner. In the current driving simulator study, 25 drivers using an advanced driving system (ADS) were randomly assigned to either an active (L2) or passive (L3) automated driving condition. Participants experienced eight near-miss driving scenarios with or without obstructions in a distributed driving …

Sparse-Data Orbit Estimation In Low Earth Orbit Using The Markov Chain Monte Carlo Ensemble Gaussian Mixture Filter, Nicholas J. Oden

Master's Theses

The number of space objects (SOs) in low Earth orbit (LEO) continues to increase rapidly, creating challenges for the current ground-based tracking network, which cannot accommodate the projected growth in SOs. Catalog maintenance relies on frequent observations for reliable reacquisition, with Two-Line Element (TLE) sets typically generated daily to mitigate rapid error growth from poor TLE accuracy. This constraint limits the ability to track more objects with existing infrastructure. This work evaluates the Markov Chain Monte Carlo Ensemble Gaussian Mixture Filter (MCMC EnGMF), a nonlinear, non-Gaussian filter well-suited for sparse tracking scenarios where higher post-update accuracy is needed to reduce …

Orbital Maneuvers And Interplanetary Trajectory Design Via Reinforcement Learning, Roberto Cuéllar Rangel

Doctoral Dissertations and Master's Theses

This dissertation investigates the application of reinforcement learning (RL) to the design and optimization of low-thrust spacecraft trajectories, with an emphasis on autonomy, adaptability, and robustness in the presence of system uncertainties and unmodeled perturbations. Classical approaches to low-thrust trajectory design are predominantly grounded in optimal control theory, which relies on the availability of precise dynamical models and often requires problem-specific reformulation and solver tuning. While optimal control methods offer high accuracy under deterministic conditions, their sensitivity to stochastic disturbances and computational limitations in highly nonlinear or uncertain environments pose significant challenges for future autonomous space missions.

To address these …

Robust Adaptive Rigid Body State And Mass Property Estimation Via Unscented Kalman Filter On Tse(3) With Process Noise Estimation, Herman Gunter

Doctoral Dissertations and Master's Theses

Mass property estimation, including mass, center of mass, and moment of inertia, is a crucial yet challenging problem in spacecraft autonomy and astrodynamics. Knowledge of mass properties of a spacecraft is essential for future astronautical missions, as changes in the mass properties of a spacecraft due to a shift in cargo distribution often require a careful and costly recalculation to ensure applied control inputs produce the desired results. As spacecraft missions grow in both duration and number, meeting the need for precise and accurate measurements becomes increasingly complex. Stochastic effects, such as angle and velocity random walks, along with persistent …

Real-Time Fiducial Marker Based Localization For Autonomous Unmanned Aerial Vehicle Navigation, Sourav Raxit

LSU New Orleans Theses and Dissertations

By harnessing fiducial markers as visual landmarks in the environment, Unmanned Aerial Vehicles (UAVs) can rapidly build precise maps and navigate spaces safely and efficiently, unlocking their potential for fluent collaboration and coexistence with humans. Existing fiducial marker methods rely on handcrafted feature extraction, which sacrifices accuracy. On the other hand, some deep learning pipelines for marker detection fail to meet real-time runtime constraints crucial for navigation applications. In this work, I propose YoloTag- a real-time fiducial marker-based localization system. YoloTag uses a lightweight YOLO v8 object detector to accurately detect fiducial markers in images while meeting the runtime constraints …

A Discrete-Time Adaptive Sliding Mode Controller For A Multicopter With A Suspended Payload, John Helzer

Department of Mechanical and Materials Engineering: Dissertations, Theses, and Student Research

This thesis presents a Discrete-time Adaptive Sliding Mode Controller (DASMC) for control of a multicopter with a suspended payload. DASMC is designed to stabilize the multicopter at a desired position while minimizing the load oscillations induced by a significant hanging payload. The proposed DASMC minimizes the need for system-specific parameters like tunable gains and improves robustness to both external disturbances and model uncertainties compared with existing controllers. The controller is designed for direct digital implementation on a variety of multicopter platforms with considerations like discrete-time design, adaptive gain shrinking, and saturation handling. When deployed on a real multicopter in an …

Experimental Analysis Of Satellite Operator Training Using Game-Based Virtual Reality Simulation, Lana Laskey

Doctoral Dissertations and Master's Theses

Satellite data plays a vital role in modern global infrastructure by enabling communications, navigation, and weather forecasting. As demand for satellite technology grows, so does the need for highly trained satellite ground operators. Traditional training regimens for satellite operators employ simulation using two-dimensional computer console displays paired with the varied ability of trainees to generate abstract mental imagery of the scenario. However, this development of mental imagery imposes a considerable learning curve and cognitive workload on the trainee, which may negatively impact the user experience and knowledge gained during the training scenario.

This experimental study investigated the effects of game-based …

Identification Of Authentic Gnss Signals In Time-Differenced Carrier-Phase Measurements With A Software-Defined Radio Receiver, Zhen Zhu, Sanjeev Gunawardena, Eric Vinande, Jason Pontious

Faculty Publications

The time-differenced carrier phase can be computed from measurements recorded by a multi-global navigation satellite system software-defined radio receiver such as PyChips, from which the user displacement and receiver clock drift can be solved. PyChips is able to simultaneously track authentic and inauthentic signals in separate channels, which makes it possible to observe both types of measurements with corresponding navigation data. A random sample consensus algorithm has been introduced to assess the consistency between the measurements and data. This algorithm successfully separated authentic channels from inauthentic channels when they are broadcast simultaneously.

Investigation Of Stability And Control Shortcomings Of The North American X-15, William Lorenzo, Ramana Grandhi, Timothy T. Takahashi

Faculty Publications

There is growing interest in the design of maneuvering high-speed aircraft to fly within or at the edge of the atmosphere. We identify and develop novel quasi-static vehicle screening methodologies, suitable for use during preliminary design, to better predict an incipient loss of control due to the dynamic effects of feedback. We validate these metrics by reverse-engineering Neil Armstrong’s 1962 loss of control and inadvertent atmospheric skip while piloting the X-15. In 1962, then-extant flight dynamics screening methods did not forecast likely troubles. We assemble and refine a collection of predictive metrics which operate upon basic quasi-static aerodynamic data and …

Development Of A Reaction Wheel System For Cal Poly’S Spacecraft Attitude Dynamics Simulator, Caleb Nalley

Master's Theses

The Cal Poly Spacecraft Attitude Dynamics Simulator (SADS) is an ongoing project to develop a system capable of simulating the attitude dynamics and kinematics of a rigid body in space. Actuations on the SADS are performed by reaction wheels, however the current reaction wheels have various issues that decrease system performance and are not independent of the SADS. The reaction wheel developed as part of this thesis will be designed to improve performance and set out design specifications tailored to the SADS, serve as an independent assembly that can be transferred to other systems, and provide a general outline for …