Towards Excellent Robotics and Artificial Intelligence at a Slovak university (Horizon Europe, GA 101079338) 2022-2025 (link)
The TERAIS project aims at transforming the Department of Applied Informatics (DAI) at Comenius University Bratislava (UKBA) to a workplace of international academic excellence and an outstanding example for other HEIs in Slovakia. To achieve this, the project aims to: (1) prepare conditions for systematic development of human capital and research capacity of DAI UKBA, (2) establish sustainable networking and collaboration links with partner institutions/within UKBA, (3) boost scientific profile of DAI towards mitigating the research and innovation gap, (4) establish institutional research support structures at UKBA. The partnership will comprise, in addition to DAI UKBA, the Knowledge Technology team at Universität Hamburg in Germany - with exceptional expertise in neural networks, deep learning and crossmodal learning for developmental robotics - and two units at Istituto Italiano di Tecnologia in Italy - with excellent experience in humanoid robotics, control using physical and simulated robots and human-robot interaction. The project will be based on 4 pillars: (1) PEOPLE - aiming at creating a life-long career development system at UKBA; (2) NETWORKING - focusing on strengthening collaboration links with international partners and the business community; (3) RESEARCH - focusing on cognitive robotics, a part of embodied artificial intelligence, in which all project partners have
outstanding expertise; and (4) SUPPORT - directed towards building the necessary research support structures at UKBA...
We aim to study specific forms of social interaction using state-of-the-art technology - virtual reality (VR) which is motivated by its known benefits. The project has two main parts, human–robot interaction (HRI) and therapist–patient interaction (TPI). The interactions are enabled using head-mounted displays and controllers allowing the human to act in VR. We propose two research avenues going beyond the state-of-the-art in respective contexts. In HRI, we will develop scenarios allowing the humanoid robot to learn, understand and imitate human motor actions using flexible feedback. Next, we develop scenarios for testing and validating human trust in robot behavior based on multimodal signals. We will also investigate physical interaction with a humanoid robot NICO. In TPI with stroke patients, we develop a series of VR-based occupational therapy procedures for motor and cognitive impairment neurorehabilitation using an active and passive brain-computer interface, and we will validate these procedures. We expect observations from HRI experiments to be exploited in TPI. The proposed project is highly multidisciplinary, combining knowledge and research methods from psychology, social cognition, robotics, machine learning and neuroscience. We expect to identify features and mechanisms leading to trustworthy processes with a human in the loop, as a precondition of success, be it a collaborative task or treatment in VR.
Computational modelling of early development of social skills in human-robot interaction (VEGA 1/0645/21) 2023-2025This project focuses on modelling early forms of human-robot collaboration, based on a developmental approach to cognition that stresses the importance of learning. The key expected contribution is in identifying a minimal set of cognitive mechanisms enabling early collaborative behaviors such as response contingency, intention recognition and turn-taking, and how these mechanisms arise from experience. We will use simple scenarios of block manipulation tasks, in which a human demonstrates a sequence of actions, such as building a tower. We will design and implement neural network models of robot’s cognitive development starting from visuomotor coordination, learning sequences by observation, replicating an observed sequence individually and also collaboratively with the human. We are planning to test two alternative realisations: physical with a robotic arm with a gripper and a stereo camera, and virtual, in which the human interacts with a simulated robotic system in virtual reality.
The project goal is to design, implement and test a robotic system (arm with a gripper, and two cameras) that would, in an interaction with a human, learn to execute commands, respond to questions, comment its own actions as well as those of a human. To make the tasks manageable, the interaction will focus on simple sensory-motor actions, such as object manipulation on a table. Project aims to yield novel insights into embodied cognitive processing and especially its developmental aspects, since most of the mechanisms will not be pre-programmed, but learned, using mostly artificial neural networks. In the sensory-motor domain, learning will be achieved by reinforcement or by human instruction, in the language domain by the human naming his/her own as well as robot’s actions. At first, different subtasks will be solved separately using the robotic simulator and then will be integrated in a physical robotic system with the same architecture.
Enhancing cognition and motor rehabilitation in mixed reality (APVV-16-0202)Technological advancements based on mixed reality (MR) offer various challenges for research and medical treatment. The project focuses on two objectives related to healthy subjects and hemiparetic patients after stroke. First, we will test the hypothesis whether cognitive training using appropriately designed MR environment will enhance perceptual and cognitive performance in healthy subjects. This will be tested by computerized psychological experiments as well as by measuring event-related potentials or ERPs. Second, we will test the hypothesis whether experience with training in MR (in combination with motor-imagery based brain-computer interface developed by us) will enhance oscillatory sensory-motor rhythms. This will be tested by measuring subject’s EEG activity before and after each training session, clinical testing, as well as by the questionnaires aiming to learn about human factors including mental fatigue, motivation, irritation or sleepiness due to training. In both objectives, we will design and implement a set of testing procedures, carry out a battery of dedicated experiments, and critically evaluate the results with the goal to validate MR designs.