Özgür S. Öğüz

About

I am an Assistant Professor in the Department of Computer Engineering at Bilkent University, where I lead the Learning for Intelligent Robotic Agents (LiRA) Lab.

Previously, I was a postdoctoral researcher at the University of Stuttgart (Machine Learning & Robotics Lab) and the Max Planck Institute for Intelligent Systems, affiliated with the Cluster of Excellence IntCDC. I received my Ph.D. (summa cum laude) in Electrical and Computer Engineering from the Technical University of Munich (TUM). I completed my prior studies in Computer Science at the University of British Columbia (UBC) and Koç University.

Research Interests

My research sits at the intersection of Robotics, Machine Learning, and Artificial Intelligence. In particular, I focus on algorithmic foundations that expand the physical capabilities of autonomous systems:

• Physical Intelligence & Embodied AI: Grounding vision-language-action (VLA) models for dexterous manipulation.
• Robot Learning: Deep reinforcement learning, imitation learning, and policy synthesis.
• Task and Motion Planning (TAMP): Logic-Geometric Programming (LGP), sequential manipulation, and hybrid planners.
• Multi-Arm & Contact-Rich Control: Optimization-augmented reactive control and dynamic tool manipulation.

LiRA Lab

At the LiRA Lab, we specialize in building active, embodied AI agents capable of perceiving, reasoning about, and interacting seamlessly with the physical world. Our laboratory infrastructure includes Franka Emika robotic arms, Vicon motion capture systems, VR teleoperation interfaces, and RGB-D sensor arrays.

Visit our lab homepage for codebases, dataset releases, and demo videos: https://lira-lab.github.io/.

Selected Publications

• CoRAL: Contact-Rich Adaptive LLM-based Control for Robotic Manipulation Berk Çiçek, Mert Kaan Er, Özgür S. Öğüz
  RSS 2026Robotics: Science and Systems
  [PDF] [Project Page] [Code]
• Lagrangian Perturbation Diffusion Steering: Latent Reinforcement Learning for Generative Policies Hikmet Şimşir, Özgür S. Öğüz
  ICML 2026Forty-Third International Conference on Machine Learning
  [PDF] [arXiv]
• Locally Adaptive One-Class Classifier Fusion with Dynamic ℓp-Norm Constraints for Robust Anomaly Detection Sepehr Nourmohammadi, Arda Sarp Yenicesu, Özgür S. Öğüz
  Pattern Recognition 2026Pattern Recognition, Vol. 171
  [Journal] [PDF]
• OpAC: An Optimization-Augmented Control Framework for Single and Coordinated Multi-Arm Robotic Manipulation Melih Özcan, Özgür S. Öğüz
  IROS 2025IEEE/RSJ International Conference on Intelligent Robots and Systems
  [PDF] [arXiv]
• SeGMan: Sequential and Guided Manipulation Planner for Robust Planning in 2D Constrained Environments Cankut Bora Tuncer, Dilruba Sultan Haliloğlu, Özgür S. Öğüz
  IROS 2025IEEE/RSJ International Conference on Intelligent Robots and Systems
  [PDF] [Video]
• H-MaP: An Iterative and Hybrid Sequential Manipulation Planner Berk Çiçek, Arda Sarp Yenicesu, Cankut Bora Tuncer, Kutay Demiray, Özgür S. Öğüz
  IEEE RA-L 2025IEEE Robotics and Automation Letters
  [IEEE Xplore] [arXiv]
• Long-Horizon Multi-Robot Rearrangement Planning for Construction Assembly Valentin N. Hartmann, Andreas Orthey, Danny Driess, Özgür S. Öğüz, Marc Toussaint
  IEEE T-RO 2022IEEE Transactions on Robotics
  [IEEE T-RO] [arXiv]
• Learning to Execute: Efficient Learning of Universal Plan-Conditioned Policies in Robotics Ingmar Schubert, Danny Driess, Özgür S. Öğüz, Marc Toussaint
  NeurIPS 2021Conference on Neural Information Processing Systems
  [NeurIPS] [Code]

Teaching

• CS 461 / CS 561: Artificial Intelligence
• CS 449 / CS 549: Learning for Robotics
• CS 491 / CS 492: Senior Design Project
• Previous: CS 342: Operating Systems

Lab Members & Students

Current Graduate Researchers:

• Berk Çiçek (M.Sc.)
• Cankut Bora Tuncer (M.Sc.)
• Mert Kaan Er (M.Sc.)
• Hikmet Şimşir (M.Sc.)
• Dilruba Sultan Haliloğlu (M.Sc.)
• Melih Özcan (M.Sc.)
• Sepehr Nourmohammadi (M.Sc.)

Alumni:

• Arda Sarp Yenicesu (M.Sc.)
• Ekin Berk Ekinci (M.Sc.)

Contact