Nataliya Kosmyna
Dr. Kosmyna is a research scientist with 16+ years of experience in developing and designing end-to-end brain-computer interfaces (BCIs). Coming from a background in artificial intelligence, neuroscience and human-computer interaction (HCI), she is passionate about the idea of creating a partnership between AI and human intelligence, a fusion of the machine with the human brain.
Most of her projects are focused around BCIs in the context of consumer grade applications. BCI applications Dr. Kosmyna is working on: recreating mental images (a process known as brain-to-image decoding), measuring engagement, fatigue or confusion of a person. Dr. Kosmyna’s projects explore ways of helping people with ALS, mvASD and other health challenges to communicate with their families, caregivers, and to control their homes or robots. Dr. Kosmyna is also interested in understanding further the true cost of using tools around us (her work on cognitive debt when using LLM chatbots), as well ways of shaping a future that benefits all of Humanity (Humans Commons Licenses).
Dr. Kosmyna’s solutions and art projects are successfully deployed in the classrooms, hospitals, workspaces, aerospace, Lower Earth Orbit, and on the Moon.
Dr. Kosmyna has served as one of 24 international experts (Ad Hoc Expert Group - AHEG) for UNESCO to help prepare a first draft of the Recommendation on the Ethics of Neurotechnology. The final text of the Recommendation was adopted in November 2025 at the 43rd session of the General Conference. She continues to serve on the Expert Advisory Group for UNESCO for this Recommendation and its adoption by Member States.
Dr. Kosmyna has also served on the Expert Advisory Group on Neurotechnology and Children for UNICEF.
Research Areas
Authored Publications
Sort By
Preview abstract
While non-verbal behaviors and expressive movements are essential for natural human-robot interaction, existing methods often overlook a crucial element: the human’s internal cognitive state. Consequently, proactive multi-agent systems frequently interrupt humans at inopportune moments, leading to cognitive overload and decreased task performance. This paper introduces a framework for generating “cognitively aligned” multi-agent interactions, enhancing the ability of robotic systems to contextually defer communications during moments of high human mental workload. We present the design and implementation of a closed-loop architecture that explores the interplay between autonomous task execution and real-time neurophysiological focus. Utilizing a consumer-grade Brain-Computer Interface (BCI), our approach continuously monitors Electroencephalography (EEG) spectral band powers while a human performs a cognitive-load-inducing task. We propose a workload-driven pipeline where an HTTP-based signaling mechanism places a primary agent’s sensory inputs and audio outputs into a holding state upon detecting high cognitive load. This allows secondary agents to seamlessly process complex, delegated tasks in the background. Once the human’s cognitive state returns to a baseline, the primary agent releases the queued agent message. Our preliminary results demonstrate the feasibility of leveraging real-time signal processing, Large Language Models (LLMs), and physical robotic embodiments to create interrupt-aware, non-intrusive multi-agent systems.
View details
