My name is Konstantinos Dermitzakis and I was born in the town of Agios Nikolaos, Crete on March 16th 1984. I have lived in Edinburgh, Scotland from September 2001 to 2006. There, I finished my undergraduate studies and obtained a BSc with Honours in Computer Science from the University of Edinburgh. I also completed my MSc studies in Artificial Intelligence at the same university. My resume is available as a document (113kb) PDF [outdated].

I am interested in the following research areas: humanoid robotics, robot kinematics and dynamics, multi-sensor fusion and sensorimotor control, machine learning and computer vision (in particular object recognition techniques). Additionally I have a particular interest in neurosciences, including cognitive modelling, computational neuroscience (specifically in how the visual system operates) and neural computation.

My research is supported through the following projects.

NCCR Robotics 3.2: sEMG-based hybrid control

Status: Active Period: 10.2011-Current

We will address the problem of reliable movement intention recognition from amputees’ residual EMG in amputees, by using information analysis techniques for better pattern discrimination and combining sEMG signals with a variety of alternative sensors to overcome the individual differences. We will also develop novel tendon-based actuation and soft tactile sensors for hand prosthetics, promoting the use of compliant mechanisms to improve the power density and adaptivity. Lastly, we will exploit the morphological and material properties (e.g. coupling through biomechanical constraints) to reduce the complexity of the control algorithm.

Dynamical Coupling in Motor-Sensory Function Substitution

Status: Completed Period: 10.2007-09.2011

Investigating the relationship between morphology, intrinsic body dynamics, information structure generation through coordinated sensory-motor activities and learning.

The goal of this project is the development of a prosthetic hand for motor-sensory function substitution which is dynamically coupled to an amputee’s sensor and motor control system. The hand will be based on EMG signals and various types of sensory feedback. By carefully investigating human upper limb dynamics and by taking into account morphological and material properties of assistive devices we hope to develop a scheme by which patients quickly learn to control the hand with less and less cognitive awareness by the user.

You can find a number of open student projects here. Note that these can also be expanded as collaborative research projects with your group. Just drop me an email for further discussion.