BEGIN:VCALENDAR
VERSION:2.0
PRODID:https://evenements.uqam.ca
X-PUBLISHED-TTL:P1W
BEGIN:VEVENT
UID:31982@https://evenements.uqam.ca
DTSTART:20251211T103000Z
SEQUENCE:6
TRANSP:OPAQUE
URL:https://evenements.uqam.ca/evenements/seminaire-au-dic-robot-learning-f
 rom-demonstration-par-sylvain-calinon/31982?date=2025-12-11_10-30-00
LOCATION:UQAM - Pavillon Président-Kennedy (PK) (201\, avenue du Présiden
 t-Kennedy\, Montréal )
SUMMARY:Séminaire au DIC: «Robot Learning from Demonstration» par Sylvai
 n Calinon
CLASS:PUBLIC
DESCRIPTION:Séminaire ayant lieu dans le cadre du Doctorat en informatique
  cognitive\, en collaboration avec le centre de recherche CRIA      
      \n\n\n \n\n\nTITRE : Robot Learning from Demonstration\n\n\n 
 \n\n\nSylvain CALINON\n\n\nJeudi le 11 décembre 2025 à 10h30\n\n\nLocal 
 PK-5115 (Il est possible d'y assister en virtuel en vous inscrivant ici)
              \n\n\n \n\n\nRÉSUMÉ\n\n\nThis talk explores h
 ow robots can efficiently acquire complex manipulation skills from minimal
  human demonstrations\, addressing one of the fundamental challenges in mo
 dern robotics. I will present approaches that exploit the inherent structu
 re and geometry of demonstration data to enable few-shot learning\, moving
  beyond traditional imitation learning that requires extensive datasets. T
 he discussion will cover representations for manipulation skills that can 
 capture task variations and coordination patterns\, optimal control techni
 ques that bridge learning and control\, and intuitive interfaces for meani
 ngful human-robot interaction. Key topics include learning on Riemannian m
 anifolds to handle orientation and manipulability constraints\, tensor met
 hods for exploiting multidimensional sensorimotor data\, and bidirectional
  interaction strategies that allow robots to actively collect better demon
 stration data. I will demonstrate applications ranging from industrial man
 ipulation tasks to assistive robotics\, showing how robots can adapt learn
 ed skills to new situations and perturbations. The talk will address both 
 the theoretical foundations of demonstration-based learning and practical 
 considerations for deploying such systems in real-world scenarios.\n\n\n 
 \n\n\nBIOGRAPHIE\n\n\nSylvain CALINON is Senior Research Scientist at the 
 Idiap Research Institute in Martigny\, Switzerland\, and Lecturer at the 
 École Polytechnique Fédérale de Lausanne (EPFL). He heads the Robot Lea
 rning &amp\; Interaction group at Idiap\, with expertise in human-robot co
 llaboration\, robot learning from demonstration\, and model-based optimiza
 tion. From 2009 to 2014\, he was Team Leader at the Department of Advanced
  Robotics\, Italian Institute of Technology (IIT). He holds a PhD from EPF
 L (2007)\, awarded the Robotdalen Scientific Award\, ABB Award\, and EPFL-
 Press Distinction. His work focuses on human-centered robotics application
 s where robots acquire new skills from few demonstrations\, developing mod
 els that exploit data structure and geometry efficiently. He has received 
 Best Paper Awards in Intelligent Service Robotics (2017) and IEEE RO-MAN (
 2007)\, and he currently serves as TC Chair on Model-based optimization fo
 r robotics for IEEE RAS.\n\n\n \n\n\nRÉFÉRENCES\n\n\nLi\, Y.\, Chi\, X.
 \, Razmjoo\, A.\, &amp\; Calinon\, S. (2024). Configuration Space Distance
  Fields for Manipulation Planning. Robotics: Science and Systems (RSS) - O
 utstanding Paper Award Finalist.\n\n\nShetty\, S.\, Lembono\, T.\, Löw\, 
 T.\, &amp\; Calinon\, S. (2023). Tensor Train for Global Optimization Prob
 lems in Robotics. IEEE RAS Best Paper Award.\n\n\nJaquier\, N.\, Rozo\, L.
 \, Calinon\, S.\, &amp\; Buerger\, M. (2019). Bayesian Optimization Meets 
 Riemannian Manifolds in Robot Learning. Conference on Robot Learning (CoRL
 ) - Best Presentation Award.\n\nMot-clés : LLMs\, LATECE UQAM INFORMATIQU
 E\, LATECE\, CRIA\, Département de Neuroscience\, Neurosciences\, Science
 s cognitives\, Philosophie\, Sciences cognitive\, École de langues\, neur
 osciences cognitives\, Institut des sciences cognitives\, Apprentissage du
  langage\, Apprentissage du langage naturel\, sciences du langage\, appren
 tissage machine\, apprentissage automatique\, apprentissage profond\, lang
 age automatique\, langage cognitif\, Cognition humaine\, Cognition\, cogni
 tion\, agent cognitif\, Intelligence émotionnelle\, Intelligence de la ma
 tière\, intelligence artificielle\, IA\; intelligence artificielle\; soci
 été\, IA\, intelligence artificielle\, chatGPT\, enseignement supérieur
 \, IA\, intelligence artificielle\, département de linguistique\, doctora
 t en psychologie\, département de psychologie\, Faculté des sciences hum
 aines\, Faculté des sciences de l'UQAM\, Faculté des sciences\, Départe
 ment d'informatique\, doctorat en informatique cognitive\, doctorat en inf
 ormatique\n\nPrix : Gratuit\n\n
CATEGORIES:Séminaire,Conférence
DTSTAMP:20260818T201926Z
CREATED:20251001T155029Z
LAST-MODIFIED:20251209T140122Z
END:VEVENT
END:VCALENDAR