I am affiliated with the following research laboratories in the Department of Computer Engineering at Istanbul Technical University.


If you are a student at want to do a graduation project or are keen on doing some research with me, for example, as a part of a Masters, see my suggested list of student projects at and send me an email or come and see me.

That list is aimed at undergraduate students but if you are a potential masters student you can start there too. In general I work in the areas of robot vision, robot learning, sensory augmentation, and artificial intelligence.

Students interested in doing their graduate research at Istanbul Technical University should have a look at the following resources:




We (about 10 of us, including 2 university staff, 4 graduate students and 4 undergraduate students) are now part way through a TÜBİTAK-sponsored project on application of deep learning methods for depth from a single image to robot applications. We have lots of ideas to explore. Send me an email on if you are interested in working with us.

This will appeal to those interested in any of:

  • Artificial intelligence and machine learning.

  • Computer Vision.

  • Human sensory processing.

  • Robotics.


We (about 10 of us, including 2 university staff, 3 graduate students and 5 undergraduate students) are now part way through a TÜBİTAK-sponsored project on sensory substitution. We have lots of ideas to explore. Send me an email on if you are interested in working with us.

This will appeal to those interested in any of:

  • Artificial intelligence and machine learning.

  • Psychology & cybernetics.

  • Assistive technologies.

  • Spatial audio and signal processing.


  • Cognitive robotics.
  • Computer vision.
  • Perception for robotics.
  • Artificial Intelligence.
  • Machine learning.
  • Integration (reasoning, motion planning, prediction, perception).
  • Mobile manipulation.
  • Assistive sensing.
  • Re-use and abstraction.
  • Physical cognition.
  • Analogy and metaphor.
  • Cognitive modelling.
  • Environmental applications.

Research Philosophy and Other Research

I am mostly working in cognitive robotics, in particular, at the intersection of computer vision, robotics, artificial intelligence, and machine learning. I am motivated by a need to study integrated embodied cognitive systems, and believe that the way toward adaptive autonomous systems is by redefining the problems studied in the sub-areas, and that we would best serve by studying integrated autonomous systems.

Part of my motivation in my research is to get close to a place from which we can understand re-use and abstraction in humans using computer models, something that will only really proceed once we have physically capable computer models (that is, robots that can reason concretely and solve a range of physical problems adaptively; that is, that are capable of a wide range of physical cognition). The study of analogy and metaphor drives these ideas from the perspective of human psychology. However, I am also motivated by the potential of this work to revolutionise waste management, environmental management, hazardous works, assistance for the disabled, industrial processes, and search and rescue; in fact, any area where autonomy is necessary, the work is degrading or harmful to humans, or the unique set of technologies on which I’m working simply find useful application.

During my PhD research at the University of Birmingham, for example, I laboured productively at moving computer vision further away from pure image processing by considering the detection and description of physical events as a core part of the vision problem. In my current research at the Sabancı University Cognitive Robotics Laboratory, I am working at the interface between reasoning, action and perception, building a perceiving, acting reasoning system for workplace mobile manipulation in difficult environments based on the Kuka YouBot, Microsoft Kinect and other sensors, as well as the ROS open source robotics ecosystem. I am also in the early stages of developing projects that integrate learning, monocular depth perception and grasping, as well as shape representation for both perception and action. Finally, I am working on the development of interfaces to depth cameras as an assistive device.


For publication statistics, see my google scholar profile:

  • Pourghaemi, H., Gholamalizadeh, T., Mhaish, A., İnce, G. & Duff, D.J. (2017). Real-time Shape-based Sensory Substitution for Object Localization and Recognition. Submitted to the Eleventh International Conference on Advances in Computer-Human (ACHI), Rome, France.
  • Gholamalizadeh, T., Pourghaemi, H., Mhaish, A., İnce, G. & Duff, D.J. (2017). Sonification of 3D Object Shape for Sensory Substitution: An Empirical Exploration. Presented at the Tenth International Conference on Advances in Computer-Human (ACHI), Nice, France. Available at
  • Mhaish, A., Gholamalizadeh, T., İnce, G. & Duff, D.J. (2016). Assessment of a visual to spatial-audio sensory substitution system. Presented at the 24th Signal Processing and Communication Application Conference (SIU), Zonguldak, Turkey. Available at
  • Duff, D. J., (2015). Orientation Averaging Using Spatial Extension. Presented at the Turkish Robotics Conference (TORK), Istanbul, Turkey. Availale at
  • Duff, D.J., Erdem, E., Patoğlu, V. (2013). Integration of 3D Object Recognition and Planning for Robotic Manipulation: A Preliminary Report. Knowledge Representation and Reasoning in Robotics Workshop at ICLP 2013, Istanbul, Turkey. Available at
  • Duff, D. J. (2011, December). Visual motion estimation and tracking of rigid bodies by physical simulation (PhD Thesis). University of Birmingham. Available at
  • Duff, D. J., Mörwald, T., Stolkin, R., & Wyatt, J. (2011). Physical simulation for monocular 3D model based tracking. In Proceedings of the IEEE International Conference on Robotics and Automation. Presented at the ICRA, Shanghai, China: IEEE. doi:doi:10.1109/ICRA.2011.5980535 – Preprint available at
  • Duff, D. J., Wyatt, J., & Stolkin, R. (2010). Motion Estimation Using Physical Simulation. In Proceedings of the IEEE International Conference on Robotics and Automation (pp. 1511–1517). Presented at the ICRA, Anchorage, AL, USA: IEEE. doi:doi:10.1109/ROBOT.2010.5509590 – Preprint available at
  • Johnson, B. W., Hautus, M. J., Duff, D. J., & Clapp, W. C. (2007). Sequential processing of interaural timing differences for sound source segregation and spatial localization: Evidence from event‐related cortical potentials. Psychophysiology44(4), 541–551. doi:10.1111/j.1469-8986.2007.00535.x – Available at,
  • Duff, D. J., & Guesgen, H. W. (2002). An Evaluation of Buffering Algorithms in Fuzzy GISs. In M. J. Egenhofer & D. M. Mark (Eds.), Geographic Information Science (Vol. 2478, pp. 80–92). Presented at the GIS, Berlin, Heidelberg: Springer Berlin Heidelberg. Available at