Séminaire ayant lieu dans le cadre du doctorat en informatique cognitive, en collaboration avec le centre de recherche CRIA et l'ISC     

Angelo CANGELOSI

Jeudi le 6 mars 2025 à 10h30

Local: PK-5115   (Il est possible d'y assister en virtuel en vous inscrivant ici)     

TITRE :   The importance of starting small: Developmental robotics for language grounding

RÉSUMÉ

Cognitive robotics aims to develop robots capable of human-like learning, interaction, and behavior by grounding abstract concepts in sensorimotor experiences and social interactions. This talk explores how principles like “starting small” and “super-embodiment” can address the limitations of AI tools, such as large language models (LLMs), which rely heavily on large datasets and static learning protocols. By integrating incremental, multimodal learning and redefining embodiment to encompass physical, mental, and social processes, we can enable robots to better understand and utilize abstract concepts. These advancements hold promise for applications in caretaking, education, and beyond, while advancing the intersection of AI, grounded intelligence, and human development.

BIOGRAPHIE

Angelo CANGELOSI, Professor of Machine Learning and Robotics at the University of Manchester and co-directs the Manchester Centre for Robotics and AI. His research focuses on cognitive and developmental robotics, neural networks, language grounding, human-robot interaction, and robot companions for health and social care. He is the author of Developmental Robotics: From Babies to Robots (MIT Press, 2015) and Cognitive Robotics (MIT Press, 2022), co-edited with Minoru Asada and Editor-in-Chief of Interaction Studies and IET Cognitive Computation and Systems.

RÉFÉRENCES

Asada, M., & Cangelosi, A. (2024). Reevaluating development and embodiment in robotics. Device, 2(11).

Elman, J. L. (1993). Learning and development in neural networks: The importance of starting small. Cognition, 48(1), 71-99.

Marchetti, A., Di Dio, C., Cangelosi, A., Manzi, F., & Massaro, D. (2023). Developing ChatGPT’s theory of mind. Frontiers in Robotics and AI, 10, 1189525.

Xie, H., Maharjan, R. S., Tavella, F., & Cangelosi, A. (2024). From Concrete to Abstract: A Multimodal Generative Approach to Abstract Concept Learning. arXiv preprint arXiv:2410.02365.