BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
X-LIC-LOCATION:America/Los_Angeles
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260417T190156Z
LOCATION:West Building\, Rooms 111-112
DTSTART;TZID=America/Los_Angeles:20250813T103000
DTEND;TZID=America/Los_Angeles:20250813T112000
UID:siggraph_SIGGRAPH 2025_sess481_ind_127@linklings.com
SUMMARY:Accelerating Embodied AI With Simulation
DESCRIPTION:Simulation is rapidly redefining how embodied AI systems learn
 , adapt, and deploy in the real world. In this talk, we’ll share best prac
 tices from Lightwheel’s work supporting leading research and industry team
 s with SimReady assets, scalable synthetic data pipelines, and simulation-
 first workflows.\nWe’ll walk through a practical sim-to-real pipeline buil
 t on top of NVIDIA Isaac Sim, Isaac Lab, OpenUSD, and GR00T-compatible inf
 rastructure, showcasing how Lightwheel enables teams to fine-tune foundati
 on models and reinforcement learning policies entirely in simulation befor
 e successful real-world deployment. We’ll highlight how high-quality, phys
 ics-accurate SimReady assets — from rigid to deformable — play a critical 
 role in generalization, and how Lightwheel’s open-source and cloud tooling
  are helping to democratize access to high-quality simulation for the broa
 der embodied AI community.\nFrom generating realistic demonstrations in si
 mulation—using validated SimReady assets for manipulation and locomotion—t
 o co-training and deploying robot foundation models like Isaac GR00T N1.5,
  this session distills hard-earned insights into what works—and what doesn
 ’t—when building generalist robots with simulation at the core.\n\nInteres
 t Area: New Technologies, Research & Education\n\nKeyword: Artificial Inte
 lligence/Machine Learning, Augmented Reality, Capture/Scanning, Computer V
 ision, Digital Twins, Generative AI, Physical AI, Pipeline Tools and Work,
  Real-Time, Rendering, Robotics, Scientific Visualization, Simulation, Spa
 tial Computing, Virtual Reality\n\nRegistration Category: Full Conference,
  Experience, Exhibits Only, Wednesday\n\n
END:VEVENT
END:VCALENDAR