Skip to main content
To KTH's start page To KTH's start page

ELSA Webinar: Privacy-Preserving Robot Learning in Human-centric Environments

Welcome to this webinar about privacy-preserving machine learning for robotics in human-centric environments. This webinar features four keynote presentations, covering a spectrum of critical topics including advanced robotic control, safe reinforcement learning, and the cutting-edge developments in both privacy-preserving and interpretable machine learning. Join us for this enlightening webinar and dive into a series of insightful discussions!

Time: Wed 2024-04-24 09.00 - 12.00

Location: Online

Video link:

Language: English

Participating: Hosts: Yuchong Zhang, Miguel Vasco

Export to calendar



  • 9:00 — 9:15 Welcome and Introduction
  • 9:15 — 9:45 Dr. Chris Pek (Delft University of Technology, Netherlands) Safe Robot Learning Through Online Verification (20 mins talk + 10 mins Q&A)
  • 9:45 — 10:15 Dr. Dmitry Kangin (Lancaster University, UK)  Towards Interpretable-by-design Machine Learning (20 mins talk + 10 mins Q&A)
  • 10:15 — 10:30 Break
  • 10:30 — 11:00 Dr. Joonas Jälkö (University of Helsinki, Finland) Privacy-preserving Machine Learning (20 mins talk + 10 mins Q&A)
  • 11:00 — 11:30 Thomas Peyrucain (PAL Robotics, Spain) Robotics in Human-centric Environments (20 mins talk + 10 mins Q&A)
  • 11:30 — 11:40 Concluding remarks


Chris Pek

Dr. Chris Pek is an Assistant Professor in the department of Cognitive Robotics (CoR) at Delft University of Technology (TUD) since 2023. Before joining TUD, he was a postdoctoral researcher at KTH Royal Institute of Technology in Sweden and a PhD student at the Technical University of Munich. His My work focuses on ensuring high degrees of safety, autonomy, and robustness of robotic systems that operate in complex environments with and around humans.

Dmitry Kangin

Dr. Dmitry Kangin (PhD Communications Systems, Lancaster University, 2016) is a Senior Research Associate at Lancaster University working for the ELSA project. He works on interpretable machine learning, focusing on computer vision, and has also been working on machine learning for science at the University of Exeter. He is an author of more than 20 publications in scientific journals and conference proceedings, including Nature. He is a member of ELLIS and regularly serves as a reviewer at leading international conferences such as ICML, ICLR, NeurIPS.

Joonas Jälkö

Dr. Joonas Jälkö is a postdoctoral researcher in Prof. Antti Honkela's group at the Department of Computer Science in University of Helsinki. Before that, he completed his PhD in Aalto University under the supervision of Prof. Samuel Kaski. His research focuses mainly on differential privacy applied on statistical inference and differentially private synthetic data.

Thomas Peyrucain

In 2020, Thomas obtained a dual degree in Mechatronics at ESIGELEC Engineering School (Rouen, France) and a Master in Robotics at Cranfield University (Cranfield, England). In 2021 he joined PAL Robotics in Barcelona as a Robotics Engineer, focusing on technical developments especially for the range of EU projects that PAL Robotics is involved in.

Yuchong Zhang

Dr. Yuchong Zhang is a postdoc fellow at KTH Royal Institute of Technology. He is working under the supervision of Prof. Danica Kragic in the Division of Robotics, Perception, and Learning. He obtained his Ph.D. from Chalmers University of Technology in 2023. His current research includes human-robot interaction, augmented/mixed reality, AI, human-centered design, visualization.

Miguel Vasco

Dr. Miguel Vasco is a postdoctoral researcher in the division of Robotics, Perception and Learning (RPL) at KTH. Before joining KTH, he acquired his PhD in 2023 at Instituto Superior Técnico, University of Lisbon. His research focuses on multimodal perception for the actuation of artificial agents, exploring adjacent areas in Representation Learning and Deep Reinforcement Learning.

This webinar is supported by the EU project ELSA European Lighthouse on Secure and Safe AI .