BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20260404T152212EDT-7448aeHWke@132.216.98.100
DTSTAMP:20260404T192212Z
DESCRIPTION:NCRN Tech Talk\n\nSpeaker: Nils Wilde\n\nAbstract:\n	In many app
 lications\, robots are required to simultaneously optimize their behaviour
  for different competing goals. For instance\, mobile platforms should com
 plete delivery tasks as quickly as possible while navigating safely and re
 specting social norms. Thus\, a central problem in human-robot interaction
  (HRI) is how users who are not experts in robotics can specify complex ob
 jectives for autonomous robots. Different users have different preferences
  for the best trade-off between objectives. We study human-in-the-loop lea
 rning frameworks that allow users to customize robot behaviour to their pr
 eferences through a sequence of simple interactions\, in particular choice
  feedback where users choose between two presented options. To learn a use
 r's preference within a few such iterations\, the robot needs to actively 
 select new options to be presented to the user. Therefore\, we are interes
 ted in exploring different optimal trade-offs for multi-objective optimiza
 tion problems\, i.e.\, the set of Pareto-optimal solutions. The applicatio
 ns of our work include high-level motion planning in human-centered enviro
 nments\, manipulation in servicing tasks\, environmental monitoring missio
 ns\, as well as multi-robot pickup and delivery.\n\nBio:\n\nNils Wilde is 
 currently a Postdoctoral Fellow in the Autonomous Multi-Robots Lab working
  with Javier Alonso-Mora at TU Delft. Until August 2021 he was a postdocto
 ral fellow at the Autonomous Systems Lab at the University of Waterloo whe
 re he also did his PhD in Electrical and Computer Engineering (ECE) under 
 the co-supervision of Dana Kulić and Stephen L. Smith from 2016 to 2020. B
 efore that he completed his BSc. and MSc. degrees at the Technical Univers
 ity Berlin in 2012 and 2016\, respectively.\n	Nils' research combines robot
  motion planning and human robot interaction (HRI)\, investigating how ine
 xperienced users can define complex behaviours for autonomous mobile robot
 s via active learning frameworks. Recent work broadens the focus to high l
 evel coordination of multi-robot systems under uncertainty as well as theo
 retical work on multi-objective optimization for robot planning problems.
 \n\n \n
DTSTART:20221201T190000Z
DTEND:20221201T200000Z
LOCATION:Zames Seminar Room\, MC 437\, McConnell Engineering Building\, CA\
 , QC\, Montreal\, H3A 0E9\, 3480 rue University
SUMMARY:Customizing Robot Behaviour through Interactive Learning
URL:https://www.mcgill.ca/cim/channels/event/customizing-robot-behaviour-th
 rough-interactive-learning-351794
END:VEVENT
END:VCALENDAR