Course Presenters: P. Maragos, P. Filntisis This course explores signal processing in modern robotics, focusing on multimodal perception, interaction, and learning. It covers fusion of audio, visual, and physiological data using deep models, human–robot interaction (affect, speech, gestures), and expressive behavior generation. It also examines self-supervised and foundation-model learning, with applications in assistive and social robotics for mobility, cognition, and special needs support.