I am a cognitive scientist specializing in developmental robotics, artificial intelligence, and cognitive modeling. Since the beginning of my research in 2005, I have been dedicated to the principles of Artificial General Intelligence (AGI). During my psychology studies, I was already creating my own cognitive architectures. I continue this work by testing cognitive architectures in humanoid robots, which I train according to the principles of developmental robotics using reinforcement learning and intrinsic motivation, utilizing advanced robotic simulators that enable the automated creation of long task sequences (lifelong learning). In my research, I connect findings from psychology and neuroscience with technical applications in robotics.
We focus on the development of embodied cognitive architectures that are based on an epigenetic robotics principles. We adopt both industrial and humanoid robots to make them learn how to understand the outside world. We develop software for training humanoid robots, such as myGym and PRAG.
Open access laboratory equipped with 64-channel EEG and eye-tracker. The laboratory serves for administering experiments in cognitive and affective neuroscience.
Research laboratory dedicated to investigating spatial cognition with a particular emphasis on reference frames and neural representations of space. The lab is equipped for EEG-based experiments that study how the human brain processes, integrates, and switches between different spatial reference frames during perception, movement, and interaction with the environment.
This European project focuses on investigating the methods that enable a collaborative robot to extract task‑relevant information from the gaze and gestures of a human partner, and how gaze, gesture, and speech information can be combined for a more natural and intuitive interface.
TERAIS (Towards Excellent Robotics and Artificial Intelligence at a Slovak University) is an international project aimed at establishing the Department of Applied Informatics of Comenius University Bratislava. Funded by the Horizon Europe programme under the Twinning call, TERAIS brings together experts from the University of Hamburg in Germany and the Italian Institute of Technology in Genoa to collaborate with scientists at DAI
The goal of the project is to design a mapping algorithm that will enable us to create such a multimodal representation of actions that incorporates prior knowledge about the uncertainty of different domains, and show how this can be used to ease teaching robotic actions and generalize them to new embodiments (e.g. different robots, grippers, etc.) and environment.
The project focuses on researching the social and technological aspects of the relationship between an elderly human user and the humanoid robot Pepper (human - robot interaction; HRI). The possibilities of using the robot to activate seniors in leisure centers for seniors are being explored.
TRADR is an integrated european research project in the area of robot-assisted disaster response. Using a proven-in-practice user-centric design methodology, TRADR develops novel science and technology for human-robot teams to assist in urban search and rescue disaster response efforts, which stretch over multiple sorties in missions that may take several days or weeks.
Inspired by the biological somatosensory cortex, this project uses the iCub humanoid robot equipped with artificial skin. It investigates how the robot can autonomously learn a representation of its own body surface (a "robotic homunculus") through tactile stimulation and self-organizing maps.
VIREAS software – Virtual Experience Kit – was developed based on a series of tests and studies among residents of a nursing home. The kit includes three virtual experiences: “Walk in the Forest”, “Walk in the City Center” and “Travel”. The interactive design combines computer graphics and 360° photography. The kit is designed to positively influence the self-expression and self-confidence of seniors, motivate them and stimulate their curiosity.
VR Bone Assembly 2.0 is an immersive educational software designed for medical students that uses virtual reality to teach human skeletal anatomy through interactive, hands-on learning. The application allows users to assemble and explore bones in a realistic 3D environment, improving spatial understanding and anatomical accuracy while reinforcing theoretical knowledge through practical engagement.
CloPeMa aims to advance the state of the art in the autonomous perception and manipulation of all kinds of fabrics, textiles and garments. Various garments will be presented in a random pile on an arbitrary background and novel ways of manipulating them (sorting, folding, etc.) will be learned on demand in a real-life dynamic environment.
Extension of Ripley robot cognitive architecture from Nikos Mavridis (MIT). A cognitive robotics project utilizing a 7-DOF manipulator with rich sensory capabilities (vision, audio, touch). The research focuses on grounding natural language semantics in perception and action, enabling collaborative tasks through spoken dialogue and interactive learning.
Neuropsychological research focused on classifying human emotional states using EEG analysis. By presenting affective stimuli (such as IAPS images), the project aims to identify specific neural correlates and feature patterns associated with different emotional responses.
In this projekct we developed applications for EEG-based neurofeedback that strongly emphasize gamification to enhance user engagement and learning outcomes. By integrating game-like mechanics such as real-time feedback, goals, rewards, and adaptive challenges, the software transforms neural self-regulation tasks into interactive experiences while maintaining rigorous experimental and clinical relevance.
An EEG-based study investigating how the human brain processes spatial information during navigation. The research differentiates between allocentric (world-centered) and egocentric (body-centered) reference frames using data from virtual environment tunnel tasks.
The presented paper contains results of pilot study in the area of human computer interaction. The proposed design is based on a subject's stay of several days in purely symbolic (text) visual environment and subsequent analysis of one´s change in production and perception of visual mental images.
This fundamental research addresses the symbol grounding problem: how abstract symbols (like words) gain meaning through connection to physical world experiences. The project develops computational models that link linguistic inputs with sensorimotor data from robotic agents.
Our generator takes as input user-defined sets of atomic actions, objects, and spatial predicates and outputs solvable tasks of a given length for the selected robotic environment. The generator produces solvable tasks by constraining all possible (nonsolvable) combinations by symbolic and physical validation.
myGym enables fast prototyping of RL in the area of robotic manipulation and navigation.You can train different robots, in several environments on various tasks. There is automatic evaluation and benchmark tool. From version 2.1 there is support for multi-step tasks, multi-reward training and multi-network architectures.
We have developed and demonstrated a system that en- ables the TIAGo++ robot to understand and execute complex, sequential commands that combine natural language and multiple pointing gestures. Our approach of decomposing commands and using a probabilistic framework for reasoning has proven to be highly effective in the planning stage.
Inverse kinematics and automatic grasping for the Nico humanoid robot.
Controlling the Pepper humanoid robot using Python.
A specialized software control library (Matlab/Python) designed for the Robotis Bioloid robot kits.
Focuses on systems that can perceive, reason, learn, and interact with the environment, often drawing inspiration from biological cognitive systems.
An introduction to the interdisciplinary study of mind and intelligence, embracing philosophy, psychology, artificial intelligence, neuroscience, linguistics, and anthropology.
Exploration of "thinking about thinking", including knowledge about when and how to use particular strategies for learning or problem-solving.
Study of the structure and function of the brain as they relate to specific psychological processes and behaviors.
Application of computational models and analytical tools to neuroscience data, bridging the gap between neuroscience and information science.
The field of study concerned with the theory and technique of psychological measurement, including the measurement of knowledge, abilities, attitudes, and personality traits.