Tony Alarcon | Portfolio

I am a Ph.D. candidate in Computer Science and Engineering at the University of Notre Dame, where I develop AI-enabled autonomy for UAV systems operating in complex and safety-critical environments. I earned my M.S. in Computer Science and Engineering from Notre Dame and previously completed a B.S. in Astrophysics at UCLA.

My research focuses on reinforcement learning, large language models, coverage path planning, and uncertainty-aware decision-making for autonomous aerial systems. I am particularly interested in building autonomy stacks that are not only intelligent, but trustworthy and deployable in real-world missions.

My work has been published across leading venues in robotics, AI, and cyber-physical systems, including ICRA, Machine Learning with Applications (MLWA), CAIN, IEEE RE, ENVIRE, and AIAA Aviation. These contributions span safe separation requirements, UAV health analytics, digital twins, and multi-agent reinforcement learning.

My work and teaching have been recognized through distinctions, honors, and awards, including the Kaneb Outstanding Graduate Teaching Assistant Award at Notre Dame, Best Data Science Project Presentation, and academic honors at Santa Monica College and UCLA.

Selected News

Jan 31, 2026	Conference acceptance: “Coverage Path Planning for Holonomic UAVs via Uniaxial-Feasible, Gap-Severity Guided Decomposition” was accepted to ICRA 2026. See you in Vienna, Austria! 🎉
May 28, 2025	Journal acceptance: “Multi-source Plume Tracing via Multi-agent Reinforcement Learning under Common UAV-faults” was accepted to Machine Learning with Applications (MLWA) 🧪
Mar 27, 2023	Project milestone: Notre Dame was selected for a NASA University Leadership Initiative (ULI) award. Led by my advisor, Prof. Jane Cleland-Huang, the multi-university SADE effort is a multi-million, multi-year collaboration advancing safe, transparent sUAS authorization for controlled airspace.

Selected Publications

ICRA

Coverage Path Planning for Holonomic UAVs via Uniaxial-Feasible, Gap-Severity Guided Decomposition

Pedro Antonio Alarcon Granadeno and Jane Cleland-Huang

Accepted at IEEE International Conference on Robotics and Automation (ICRA), 2025

Vienna, Austria, 2026 (to appear)

arXiv Bib Code

@article{aa2025coverage,
  title = {Coverage Path Planning for Holonomic UAVs via Uniaxial-Feasible, Gap-Severity Guided Decomposition},
  author = {Granadeno, Pedro Antonio Alarcon and Cleland-Huang, Jane},
  journal = {Accepted at IEEE International Conference on Robotics and Automation (ICRA)},
  year = {2025},
  list_order = {y2025_01},
  note = {Vienna, Austria, 2026 (to appear)},
}

MLWA

Multi-source plume tracing via multi-agent reinforcement learning under Common UAV-faults

Pedro Antonio Alarcon Granadeno, Theodore Chambers, and Jane Cleland-Huang

Machine Learning with Applications, 2025

DOI arXiv Bib Code

@article{ac2025plume,
  title = {Multi-source plume tracing via multi-agent reinforcement learning under Common UAV-faults},
  author = {Granadeno, Pedro Antonio Alarcon and Chambers, Theodore and Cleland-Huang, Jane},
  journal = {Machine Learning with Applications},
  pages = {100737},
  year = {2025},
  list_order = {y2025_03},
  publisher = {Elsevier},
  doi = {10.1016/j.mlwa.2025.100737},
}

Selected Projects

Coverage Path Planning for Holonomic UAVs

Gap-severity guided decomposition for complete, efficient, and robust coverage.