Dr.-Ing. Özgür S. Ögüz

Email: o.oguz(at)tum.de

Short Biography

2022	Professor at Bilkent University, following positions as a Post-doctoral Researcher at the University of Stuttgart and Max Planck Institute for Intelligent Systems
2018	PhD Thesis: Natural Human-Robot Interaction in Close Proximity: A Human-in-the-Center Approach Technical University Munich, Germany (TUM)
2014 - 2019	Research Assistant Chair of Automatic Control Engineering Technical University Munich, Germany (TUM)
2010 - 2012	Teaching Assistant and Graduate Student University of British Columbia, Canada
2010	Master Thesis: Haptic Negotiation and Role Exchange for Collaboration in Virtual Environments Koc University, Turkey
2007	B.Sc., M.Sc. (summa cum laude) Electrical And Computer Engineering Koc University, Turkey

 

Research Interests

My research focuses on developing novel control, optimization and learning algorithms to provide necessary and safe robotic assistance to humans. The specific topics of interest are:

• (Inverse) Reinforcement Learning
• (Inverse) Optimal Control 
• Human Sensorimotor Control
• Safe Learning for close proximity HRI/C

Open Positions

Looking for motivated students to work on projects/thesis topics related to:

• Human-Robot Interaction & Collaboration (HRI/C)
• (Deep) Learning and Optimal Control for HRI/C

Publications (Recent)

• Ozgur S. Oguz, Ben Pfirrmann, Mingpan Guo and Dirk Wolherr (2018): Learning Hand Movement Interaction Control Using RNNs: From HHI to HRI, NeurIPS Imitation Learning and its Challenges in Robotics Workshop, Dec. 2018. (online) (video) (code).

• Ozgur S. Oguz, Ben Pfirrmann, Mingpan Guo  and Dirk Wolherr (2018): Learning Hand Movement Interaction Control Using RNNs: From HHI to HRI, Robotics and Automation Letters (RA:L), vol. 3, no. 4, pp. 4100-4107, Oct. 2018. (online) (video) (code).

• Ozgur S. Oguz, Zhehua Zhou, Stefan Glasauer and Dirk Wolherr (2018), An Inverse Optimal Control Approach to Explain Human Arm Reaching Control Based on Multiple Internal Models, Nature Scientific Reports, vol 8, 1, 5583 (pdf, online).

• Ozgur S. Oguz, Zhehua Zhou and Dirk Wolherr (2018), A Hybrid Framework for Understanding and Predicting Human Reaching Motions, Frontiers in Robotics and AI, vol 5, 27 (online).

• Ozgur S. Oguz, Omer C. Sari, Khoi H. Dinh and Dirk Wollherr (2017): Progressive Stochastic Motion Planning for Human-Robot Interaction, Proceedings of the 26th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN 2017). 

• Ozgur S. Oguz, Wolfgang Rampeltshammer and Dirk Wolherr: An Ontology for Human-Human Interaction and Learning Interaction Behavior Models, Transactions on Human-Robot Interaction (THRI) (under review).

• Ozgur S. Oguz, Ahmed Magdy and Dirk Wolherr: A Hybrid Approach for Constrained Deep Reinforcement Learning, (preprint).

Publications (Prior to LSR)

• Ozgur S. Oguz, Ayse Kucukyilmaz, Tevfik M. Sezgin, Cagatay Basdogan, Improving human-computer cooperation through haptic role exchange and negotiation, (Book Chapter) Immersive Multimodal Interactive Presence, 229-254, 2012.

• Ozgur S. Oguz, Ayse Kucukyilmaz, Tevfik M. Sezgin, Cagatay Basdogan, Supporting negotiation behavior with haptics-enabled human-computer interfaces, IEEE transactions on haptics 5 (3), 274-284, 2012. 

• Ozgur S. Oguz, Ayse Kucukyilmaz, Tevfik M. Sezgin, Cagatay Basdogan, Haptic negotiation and role exchange for collaboration in virtual environments, IEEE Haptics Symposium, 2010.

• Ozgur S. Oguz, Ayse Kucukyilmaz, Tevfik M. Sezgin, Cagatay Basdogan, Collaborative Haptic Negotiation and Role Exchange in Multimodal Virtual Environments, CSW 1 st Computer Science Student Workshop, 2010.