Ege Yuceel

I'm a second-year Ph.D. student in the Reliable Autonomy Group at the University of Illinois Urbana-Champaign (UIUC), advised by Prof. Sayan Mitra. My research lies in robotics — particularly fast and efficient motion planning algorithms and planning and localization under limited information, with applications to aerial robotics.

Previously, I received my B.Sc. in Electrical and Electronics Engineering from Bilkent University, where I worked with Dr. Muhammed Ömer Sayın in the Games, Decisions, and Networks Lab on multi-agent learning and game theory.

Email / CV / Scholar / Github

News

May 2026 — Started as a Research Intern at Toyota Research Institute of North America (TRINA).
May 2026 — Active Localization of Unstable Systems with Coarse Information received the Best Paper Award (Foundations Track) at HSCC 2026.
May 2026 — Received my M.S. in Electrical and Computer Engineering from UIUC.
April 2026 — Passed my Ph.D. qualifying exam.
April 2026 — Omniscient Attacker in Stochastic Security Games with Interdependent Nodes was accepted to the IFAC World Congress 2026.
January 2026 — Performance-Guided Refinement for Visual Aerial Navigation using Editable Gaussian Splatting in FalconGym 2.0 was accepted to ICRA 2026.

Selected Work

	Active Localization of Unstable Systems with Coarse Information Ege Yuceel, Daniel Liberzon, Sayan Mitra ACM International Conference on Hybrid Systems: Computation and Control (HSCC), 2026 (Best Paper Award — Foundations Track) arXiv Active localization of unstable linear systems from coarse, quantized measurements, with soundness and completeness guarantees on the recovered localization set.
	Performance-Guided Refinement for Visual Aerial Navigation using Editable Gaussian Splatting in FalconGym 2.0 Yan Miao, Ege Yuceel, Georgios Fainekos, Bardh Hoxha, Hideki Okamoto, Sayan Mitra IEEE International Conference on Robotics and Automation (ICRA), 2026 arXiv Performance-guided refinement for visual aerial navigation: editable Gaussian splatting builds photorealistic scenes, enabling zero-shot vision-based flight through gates across diverse environments.
	Minimal Information Control Invariance via Vector Quantization Ege Yuceel, Teodor Tchalakov, Sayan Mitra arXiv preprint, 2026 arXiv An encoder–codebook–decoder that maps observations to a finite set of control regions via vector quantization, achieving control invariance with minimal information.
	Factored Diffusion Policies: Compositionally Generalized Robot Control with a Single Score Network Sayan Mitra, Ege Yuceel, Noah Giles, Abhishek Pai arXiv preprint, 2026 arXiv A single score network whose factored structure compositionally generalizes robot control to unseen task and environment combinations, including zero-shot transfer.
	Omniscient Attacker in Stochastic Security Games with Interdependent Nodes Yuksel Arslantas, Ahmet Said Donmez, Ege Yuceel, Muhammed O. Sayin IFAC World Congress, 2026 arXiv Stochastic security games over interdependent nodes modeled as a linear influence network, analyzing an omniscient attacker against a learning defender.
	Convergence of Heterogeneous Learning Dynamics in Zero-sum Stochastic Games Yuksel Arslantas, Ege Yuceel, Yigit Yalin, Muhammed O. Sayin IEEE Transactions on Automatic Control (TAC), 2025 IEEE Xplore Convergence analysis of heterogeneous learning dynamics, where agents run different update rules, in zero-sum stochastic games.
	Strategizing against Q-learners: A Control-theoretical Approach Yuksel Arslantas, Ege Yuceel, Muhammed O. Sayin IEEE Control Systems Letters (L-CSS), 2024 IEEE Xplore A control-theoretical framework for a strategic agent to exploit and steer Q-learning opponents toward favorable outcomes.

The source code of this website has been taken from here.