Axel Muñiz Tello

[Research Project Title]

Research Focus: Brief description of your research project, including the problem you're investigating, methodologies you're using, and the significance of the work.

Key Contributions: Highlight your specific contributions to the project, such as experimental design, data analysis, or theoretical framework development.

Technologies/Methods: [Method 1], [Method 2], [Tool/Software 1], [Tool/Software 2]

[Second Research Project]

Research Focus: Description of another research experience, including objectives, approaches, and outcomes.

Key Contributions: Your role and contributions to the research project.

Technologies/Methods: [Method 1], [Method 2], [Tool/Software 1], [Tool/Software 2]

[Independent Research or Third Project]

Research Focus: Brief description of additional research work, including any independent studies or collaborative projects.

Key Contributions: What you accomplished and learned from this experience.

[Project Name] [GitHub]

Description of your personal project. Explain what problem it solves, what motivated you to build it, and what technologies or frameworks you used. Include any interesting challenges you overcame or unique features you implemented.

Impact/Results: Quantify results if possible (e.g., number of users, performance improvements, insights gained).

[Second Project Name] [GitHub]

Description of another personal project. Highlight technical complexity, creative solutions, and what you learned from building it.

Impact/Results: Key outcomes and learnings from the project.

[Third Project Name] [Demo/Link]

Description of a third project. This could be a hackathon project, course project, or any other technical work that showcases your skills and interests.

Robustness and Conditioning of Recursive Least Squares in Adaptive Cruise Control Systems

Authors: Axel Muñiz Tello, Ayush Pandey

As Adaptive Cruise Control (ACC) systems become more common, maintaining string stability is critical for safety and traffic efficiency. This study examines how parameter excitability in the regressor matrix influences the accuracy and adaptability of ACC systems. Using a Recursive Least Squares algorithm for online parameter estimation, we found that low excitation reduces sensitivity and leads to poor parameter convergence, especially during steady-speed driving. High-excitation conditions such as curves or aggressive maneuvers improve estimator performance and system responsiveness. Simulations across multiple driving conditions show that realistic, variable excitation produces more stable and reliable results. These findings highlight that traffic variability is not noise but a key ingredient for developing smarter, safer, and more adaptable automated driving systems.

[Coming Soon]

Benchmarking U-Net and Neural Cellular Automata (NCA) for Amodal Segmentation

Presenters: Axel Muñiz Tello, Melanie Gomez-Bustos, Wesley Hur, Eddie Lizarzaburu

This research investigates the application of computer vision techniques to synthetic data for training models aimed at automating laboratory processes. By integrating simulation-based datasets with machine learning methods, we seek to enhance the reliability and scalability of automated experimental workflows. The project provided hands-on experience in data science, computational modeling, and algorithmic design, while fostering collaboration with domain experts. Through this work, we demonstrate the potential of synthetic training data to accelerate innovation in automated scientific research environments.

View Poster

Modeling Disease Dynamics Using Kinetic Monte Carlo

Presenters: Axel Muñiz Tello

This research explores disease transmission dynamics using Kinetic Monte Carlo (KMC) simulations within an agent-based SIR framework. By modeling populations on lattice structures with both restricted and unrestricted movement, it examines how spatial structure and randomness influence infection and recovery patterns. The study highlights how spatial constraints and stochastic effects shape epidemic behavior, offering insights for improving future disease control strategies.

View SIAM Presentation | View [Second Conference] Presentation