Trusted AI

Our department conducts research in Applied Artificial Intelligence, with a focus on robotics and nonlinear control, neuroscience, big data analytics, energy transition and sustainability, agentic AI, and knowledge representation. The department also addresses challenges related to the deployment of AI models in distributed and resource-constrained environments.

In robotics and nonlinear control, research activities cover intelligent perception and robot control, AI-driven methods for nonlinear optimal control, networked systems, and state estimation, as well as foundational algorithms and software for reinforcement learning and deep neural networks. These methods are applied in marine, ground, and aerial robotics, precision agriculture, medicine, rehabilitation robotics, and related domains.

Research in** neuroscience** focuses on the development of machine learning techniques for spike sorting, burst detection, EEG data analysis, and functional brain network mapping using graph neural models. In collaboration with the Transylvanian Institute of Neuroscience, the department develops computational tools for analyzing neural and brain activity.

In the area of big data analytics, research teams develop and adapt advanced AI techniques, including Transformer architectures, large language models, deep neural networks, and reinforcement learning, to support decision-making and enable predictive and descriptive analytics. Representative applications include predictive maintenance, modeling user behavior in household environments, and energy consumption profiling. Research also addresses scalable storage systems, data visualization, and preprocessing techniques for data cleaning and transformation. Although much of the work focuses on IoT data, the developed methodologies are broadly applicable to other data domains.

In the area of energy management and sustainability, research focuses on advanced AI, blockchain, and distributed control techniques that support decision-making in energy network management and enable predictive analyses related to energy demand and supply, consumption optimization, and renewable energy integration. These approaches contribute to the development of decentralized, secure, and privacy-preserving energy markets, as well as to the modeling and digitization of industrial processes. Research activities also include the design and implementation of smart contracts for automated energy transactions, AI mechanisms for peer-to-peer energy trading without trusted intermediaries, and tokenized ecosystems that incentivize distributed energy production and prosumer participation.

Research themes also include the development of explainable AI models and algorithms capable of providing transparent and interpretable decision-making processes, which are essential for deploying AI systems in sensitive and high-impact domains.

Research on agentic and knowledge-based AI focuses on autonomous agents, multi-agent systems, semantic technologies, and knowledge representation methods that enable intelligent reasoning, adaptive decision-making, and human-centered AI applications. These approaches support the development of collaborative, context-aware, and trustworthy AI systems capable of operating in dynamic and distributed environments.