Robots, Infants & Chicks :

Embodied Learning Mechanisms in The
Real-World

Sep 16th, Full-Day (9:00 - 17:30) Czech Technical University, Prague

About

How do learners make sense of the noisy, complex data of the real world?
Robots, infants, and chicks may use a common solution: embodied learning. By interacting with their environments, robots, infants, and chicks generate their own diverse, but temporally coherent, training data. Their actions in one moment elicit responses from the environment that in turn impact their subsequent actions. This continuous dynamic feedback loop offers embodied learners flexibility to overcome the complexity of the real-world. Interdisciplinary insights and discussions integrating robotics, cognitive science, and developmental psychology research can lead to more efficient learning systems.



Speakers

Professor Minoru Asada
Vice-President
International Professional University of Technology in Osaka, Japan

Specially-Appointed Professor
and Strategic Adviser
Symbiotic Intelligent System Research Center
Open and Transdisciplinary Research Initiatives
The University of Osaka, Japan
Professor Giorgio Metta
Scientific Director
Istituto Italiano di Tecnologia
Professor Samantha Wood
Assistant Professor of Informatics
Luddy School of Informatics, Computing, and Engineering
Indiana University Bloomington
Dr. Hadar Kaarmazyn-Raz
Postdoctoral Fellow
Cognitive Development Lab
Indiana University Bloomington
Merkourios Simos
PhD Graduate Student
Mathis Group for Computational Neuroscience & AI
EPFL, Geneva, Switzerland

Schedule

Biological Organisms


8:50 - 9:00

Welcome & Intro to The Workshop


Prresenting research on parallel controlled-rearing experiments with animals and artificial intelligence (AI) models. Newborn brains exhibit remarkable abilities in rapid and generative learning, but what are the necessary “ingredients” for perceiving and understanding the world around us?


9:45 - 10:30


Presenting children's uncontrolled free-flowing play to show how memory relations - emergent in actions on objects - create a coherent network of associations among handled toys.



10:30 - 11:00

Coffee IconCoffee Break

11:00 - 11:45

Activity & Discussion

Hands-on interactive demonstrations of self-generated data for learning

Robots

11:45 - 12:30


Presenting research on human-robot collaboration. Human-robot collaboration is a challenging task that requires developing artificial perceptual skills to interpret human behaviors and exquisite timing to react seamlessly to such behaviors.



12:30 - 14:00

Coffee IconLunch Break

14:00 - 14:45


Presenting his paper on artificial empathy outlining the developmental trajectory of empathy, beginning with emotional contagion, followed by emotional empathy, cognitive empathy, and ultimately, sympathy and compassion.


14:45 - 15:30



Presenting KINESIS, a framework exploring how complex embodied agents learn from demonstrations.



15:30 - 16:00

Coffee IconCoffee Break

16:00 - 17:00

Activities

Hands-on interactive demonstrations of embodied engagement with real-world environment
and how these engagements form systems of knowledge.

17:00 - 17:30

General Discussion and Closing Remarks