TECoSA Seminar – Cloud Robotics for Data-Driven Robotic Manipulation Research at Scale

We aim to bring you a TECoSA Seminar on the first Thursday of each month during term-time. For Spring 2023, the talks will be on-line or hybrid. All are welcome to attend and we look forward to some lively discussions. Members can accept the invitations, non-members can email tecosa-admin@kth.se to register.

Our May seminar is with Florian Pokorny, Associate Professor of Machine Learning at the Division of Robotics, Perception and Learning here at KTH.

23.04.28 update: Please note that this event will take place in Zoom only: https://kth-se.zoom.us/j/66857695267 (not in Digital Futures Cafeteria as previously announced).

ABSTRACT: In this talk, Dr Pokorny will discuss the challenges and opportunities surrounding large scale experimentation for machine learning driven robotic manipulation research. While it is accepted wisdom that the performance of state of the art machine learning algorithms in fields like language modelling and computer vision scales directly with available input data, compute and model size, many open questions regarding these scaling laws remain when it comes to physical interactions of robotic systems with the world, where the complexity of data-driven learning may depend heavily on the physical characteristics of a given robotic manipulation task.  He will discuss some of his group’s research in this direction, as well as the development of a new open source robotic system which will allow large scale execution of robotic experiments in a massively parallelized manner using a Cloud Robotics approach.

BIO: Dr Pokorny’s current research focuses on two main directions: 1) machine learning algorithms with a geometric or topological flavour or which utilize insights about geometry in the context of other methods such as deep learning and 2) machine learning methods that are tailored for robotic manipulation or motion planning and which incorporate available domain knowledge and information about physics and configuration space geometry in order to be data efficient.  You can read more on his homepage: https://www.csc.kth.se/~fpokorny/