Tatiana Gutierrez

I am a Ph.D. Student at Embry-Riddle Aeronautical University (ERAU) in Daytona Beach, FL . As a graduate student, I have worked on projects broadly related to Multi-agent Systems, Optimal Control and Adaptive Control .

I currently have a graduate research fellowship GAANN funded by the U.S. Department of Education and ERAU. I obtained my M.Sc degree in Aerospace Engineering (2022).

Email  /  CV  /  Google Scholar  /  Github

Research

For my research work, I am interested in exploring trajectory optimization and safe-control methods for spacecraft and aircraft systems. My main goal involves developing an optimization framework for path reconfiguration when faults or unexpected situations occur, that threatens the mission goals. For this end, I am currently learning about convex optimization and exploring CVX, NAIF and SBDT toolbox software in MATLAB.

Thesis

This research applies an optimized health monitoring system capable of detecting nominal and off-nominal system conditions. A simulation environment is developed for a fleet of spacecraft performing a low-Earth orbit inspection within close proximity of a target space asset. An adaptive control based on Deep Reinforcement Learning using an Actor-Critic-Adverse architecture is implemented to achieve high levels of mission protection, especially under disturbances that might lead to performance degradation. A comparison of different attitude controllers such as Nonlinear Dynamic Inversion and Pole Placement is presented.

Publications

This paper presents the design, validation, and verification of AI-based algorithms by implementing three attitude controllers onto a spacecraft testbed: a Nonlinear Dynamic Inversion controller augmented with Artificial Immune System (NLDI-AIS), a Fuzzy-Logic based controller, and a Deep-Reinforcement Learning Adaptive Controller (DRL).

The proposed HMS is applied to a design reference mission that involves a fleet of spacecraft performing an on-orbit inspectionin low Earth orbit. The performance and capabilities of the architecture are validated throughnumerical simulations where spacecraft in the network are subjected to various faults.

This paper aims to quantitively estimate the shadowing and multi-path effects for a simulated Unmanned Aerial Vehicle (UAV) mission within an urban environment scenario. Furthermore, the impact of signal degradation effects is analyzed by evaluating GPS constellation quality metrics such as the Dilution of Precision (DOP).

This paper describes the design, integration, and implementation of a set of software tools to support validation and verification of guidance, navigation, and control strategies applied to unmanned system operations.

This paper describes the design and development of a novel bioinspired distributed adaptive control architecture designed to increase the resilience of multiagent systems. Numerical simulations are performed to evaluate the capabilities of this architecture to solve a consensus problem under bounded disturbances. Stability analysis is presented using the Lyapunov direct method.

Thispaper introduces a novel bio-inspired immunized-adaptive technique applied to a multi-agentconsensus control problem in the presence of bounded time-varying disturbances and cyber-physical communication attacks. Analyses of the capabilities of the controller to reject thesedisturbances, and a comparison against an adversarial deep-reinforcement learning algorithmis presented.

Internships

Supervisors: Rob Tappan and Simon Hales

I made modifications to simulation models (Matlab/Simulink), assisted with code bugfixes, builded user interface commands (C++, C#), assisted with the development/maintenance of application and embedded technologies.

• Converted configurable subsystems to variant subsystems in Simulink Model
• Implemented variant subsystems to switch between vehicles configuration.
• Included new controls to Sim User Interface so GPS signal is reduced in certain conditions.

I borrowed this website layout from here!