BEGIN:VCALENDAR
CALSCALE:GREGORIAN
VERSION:2.0
METHOD:PUBLISH
PRODID:-//Drupal iCal API//EN
X-WR-TIMEZONE:America/New_York
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
DTSTART:20070311T020000
TZNAME:EDT
TZOFFSETTO:-0400
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
DTSTART:20071104T020000
TZNAME:EST
TZOFFSETTO:-0500
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
SEQUENCE:1
X-APPLE-TRAVEL-ADVISORY-BEHAVIOR:AUTOMATIC
204156
20250211T145002Z
DTSTART;TZID=America/New_York:20250218T150000
DTEND;TZID=America/New_York:2
 0250218T160000
URL;TYPE=URI:/news/calendar/events/robot
 ics-engineering-colloquium-speaker-dr-wei-xiao
Robotics Engineering Colloquium Speaker - Dr. Wei Xiao
Certifiable Neural Control for Safe Autonomyand Robotics\n\n\n\n      \n      \n\n\n\nAbstract:
  Safety is central to autonomous systems and robots since a single failure
  could lead to catastrophic results. In unstructured complex environments 
 where system states and environment information are not available, the saf
 ety-critical control problem is much more challenging. In this talk, I wil
 l first discuss safety from a control theoretic perspective with Control B
 arrier Functions (CBFs). CBFs capture the evolution of the safety requirem
 ents during the execution of a control system and can be used to guarantee
  safety for all times due to their forward invariance. Next, this talk wil
 l introduce an approach for extending the use of CBFs to machine learning-
 based control, using differentiable CBFs that are end-to-end trainable and
  adaptively guarantee safety using environmental dependencies. These novel
  safety layers give rise to new neural network (NN) architectures such as 
 what we have termed BarrierNet. In machine learning and robot learning, th
 e interpretability of a NN is crucial. The talk will further introduce a n
 ovel method called invariance propagation through the NN. This approach en
 ables causal reasoning of the NN's parameters or inputs with respect to ro
 bot behaviors, as well as introducing guarantees. Finally, I will show how
  we can certify more powerful generative AI, such as diffusion models, for
  generalizable and safe autonomy and robotics. These techniques have been 
 successfully applied to various robotic systems, such as autonomous ground
  vehicles, surface vessels, and flight vehicles, legged robots, robot swar
 ms, soft robots, and manipulators.\nBio: Wei Xiao is currently a postdocto
 ral associate at the Computer Science and Artificial Intelligence lab (CSA
 IL), Massachusetts Institute of Technology. He received his Ph.D. degree f
 rom the Boston University, Brookline, MA, USA in 2021. His research intere
 sts include safety-critical control theory and trustworthy machine learnin
 g, with a particular emphasis on robotics. He received an Outstanding Diss
 ertation Award at Boston University, an Outstanding Student Paper Award at
  the 2020 IEEE Conference on Decision and Control, and a Best Paper Nomina
 tion at ACM/IEEE ICCPS 2021.\nZoom link: https://wpi.zoom.us/j/93413349160
 \n
END:VEVENT
END:VCALENDAR