BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
BEGIN:DAYLIGHT
DTSTART:20250309T030000
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:PDT
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20251102T010000
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:PST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20251105T034153Z
UID:7E1158DA-8007-48AC-AFD9-0A7DCC080967
DTSTART;TZID=America/Los_Angeles:20250623T185000
DTEND;TZID=America/Los_Angeles:20250623T200000
DESCRIPTION:Advances in flexible\, deployable\, and deformable structures a
 nd sensors require efficient simulation tools that capture nonlinear geome
 try and material behavior. We propose a machine learning (ML) approach usi
 ng neural networks (NN) to simplify simulations\, enabling the creation of
  digital twins and facilitating sim-to-real transfer in structural mechani
 cs.\n\nThis talk presents a case study using neural networks (NN) to creat
 e a reduced-order model for the dynamic simulation of a slinky\, a popular
  children’s toy made of a pre-compressed helical spring that can stretch
  and deform. Instead of simulating the entire 3D structure of the slinky\,
  we use a reduced representation based on the deformation of its helix axi
 s\, significantly reducing the degrees of freedom (DOFs). The mechanics of
  this simplified representation are captured using a neural ordinary diffe
 rential equation (neural ODE)\, trained with data from high-resolution 3D 
 simulations. This approach enables faster dynamic simulations while mainta
 ining physical accuracy\, and thanks to the physics-based nature of our mo
 del trained with neural ODEs\, it is highly generalizable—adapting to ch
 anges in boundary conditions or external forces without the need for retra
 ining.\n\nThe second part of the talk introduces DiSMech\, an open-source 
 software platform for fast simulations of flexible structures\, which was 
 used in the slinky study. DiSMech aims to enable researchers at all levels
  to explore the mechanics of soft robots and flexible structures/sensors\,
  driving innovation in robotics research and education. Built on a discret
 e differential geometry (DDG) approach\, it offers a practical alternative
  to computationally intensive conventional simulation tools.\n\nSpeaker(s)
 : Dr. M. Khalid Jawed\n\nAgenda: \n6:50 - 7 PM: Registration\n\n7-8 PM: Ta
 lk and Q&A\n\nVirtual: https://events.vtools.ieee.org/m/489214
LOCATION:Virtual: https://events.vtools.ieee.org/m/489214
ORGANIZER:bherrera@qti.qualcomm.com
SEQUENCE:36
SUMMARY:Machine Learning-assisted Physics-based Simulation & Control of Fle
 xible Structures\, Sensors and Soft Robots
URL;VALUE=URI:https://events.vtools.ieee.org/m/489214
X-ALT-DESC:Description: <br /><div dir="auto">Advances in flexible\, deploy
 able\, and deformable structures and sensors require efficient simulation 
 tools that capture nonlinear geometry and material behavior. We propose a 
 machine learning (ML) approach using neural networks (NN) to simplify simu
 lations\, enabling the creation of digital twins and facilitating sim-to-r
 eal transfer in structural mechanics.</div>\n<div dir="auto">&nbsp\;</div>
 \n<div dir="auto">This talk presents a case study using neural networks (N
 N) to create a reduced-order model for the dynamic simulation of a slinky\
 , a popular children&rsquo\;s toy made of a pre-compressed helical spring 
 that can stretch and deform. Instead of simulating the entire 3D structure
  of the slinky\, we use a reduced representation based on the deformation 
 of its helix axis\, significantly reducing the degrees of freedom (DOFs). 
 The mechanics of this simplified representation are captured using a neura
 l ordinary differential equation (neural ODE)\, trained with data from hig
 h-resolution 3D simulations. This approach enables faster dynamic simulati
 ons while maintaining physical accuracy\, and thanks to the physics-based 
 nature of our model trained with neural ODEs\, it is highly generalizable&
 mdash\;adapting to changes in boundary conditions or external forces witho
 ut the need for retraining.</div>\n<div dir="auto">&nbsp\;</div>\n<div dir
 ="auto">The second part of the talk introduces DiSMech\, an open-source so
 ftware platform for fast simulations of flexible structures\, which was us
 ed in the slinky study. DiSMech aims to enable researchers at all levels t
 o explore the mechanics of soft robots and flexible structures/sensors\, d
 riving innovation in robotics research and education. Built on a discrete 
 differential geometry (DDG) approach\, it offers a practical alternative t
 o computationally intensive conventional simulation tools.</div>\n<div dir
 ="auto">&nbsp\;</div><br /><br />Agenda: <br /><p>6:50 - 7 PM: Registratio
 n</p>\n<p>7-8 PM: Talk and Q&amp\;A</p>
END:VEVENT
END:VCALENDAR