We investigate a range of deep neural network and deep reinforcement learning models to support medical decision-making, human action recognition, and autonomous driving.

At the same time, we explore explainable AI (XAI) methods aimed at increasing the transparency of black-box models.

Our work also focuses on coordination mechanisms, automated negotiation in multi-agent systems, agent learning, and the formation and coordination of robotic swarms developed within our laboratory.

We also employ computer vision and planning techniques to create specialized software for social robots capable of interacting with people, interpreting human actions, and responding appropriately. This enables multimodal interaction with assistive robots intended to enhance the well-being of older adults and individuals with special needs.