BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:On Feedback Error Learning for Adaptive Soft Robot Control
DTSTART:20241003T110000
DTEND:20241003T120000
DTSTAMP:20260607T011319Z
UID:3912e98d06af91df6ea41ae7cad1bd36824564c0d7b87b914fff76da
CATEGORIES:Conferences - Seminars
DESCRIPTION:Niccolò Enrico Veronese\, Politecnico di Milano\nAbstract\nT
 his talk aims to explore how Feedback Error Learning (FEL) framework can b
 e used to generate online learning\ncapabilities for soft robot control.\n
 Soft robots are appealing in a wide variety of tasks thanks to their inher
 ent advantages in safety\, compliance\, and\nadaptability. However\, accur
 ate modelling and control of soft robots are still significantly challengi
 ng. For these\nreasons we proposed the FEL architecture which is composed 
 of (i) a data-driven model generating a feedforward\nsignal\, and (ii) a f
 eedback controller. The latter has two roles. Firstly\, it corrects the ac
 tion of the feedforward\ncontroller when the tracking error increases. Sec
 ondly\, it generates a learning signal to train the data-driven\nmodel\, a
 llowing for online adaptation of the feedforward signal with respect to ch
 anges in the dynamic of the\nsystem.\n\nBiography\nNiccolò Enrico Verones
 e is a fellow researcher on Robotics and Control at Politecnico di Milano.
 \nHe received the B.Sc. degree and M.Sc. degree\, both with honours\, from
  Politecnico di Milano\, Italy\, in 2021 and\n2023\, respectively. He deve
 loped his master thesis at the University of Oxford\, UK\, within the Oxfo
 rd Robotics\nInstitute in close collaboration with the Control Group of Un
 iversity of Cambridge\, UK. He presented two papers\non Control and Reinfo
 rcement Learning for soft robots at the IEEE Robosoft Conference 2024 in S
 an Diego\, CA\,\nand authored a review paper on Additive Manufacturing\, p
 ublished in Progress in Material Science. Niccolò is an\nalumnus of the A
 lta Scuola Politecnica\, an interdisciplinary honours program for 150 top 
 students from\nPolitecnico di Milano and Politecnico di Torino.\nHis resea
 rch interests focus on control and machine learning architectures\, partic
 ularly their applications in\nrobotics\, automation and soft robotics.
LOCATION:ME C2 405 https://plan.epfl.ch/?room==ME%20C2%20405
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR