BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
X-WR-CALNAME:ECE Seminar: Sabrina M. Neuman\, Designing Computing Systems f
 or Robotics and Physically Embodied Deployments
X-WR-TIMEZONE:Eastern Time (US & Canada)
BEGIN:VEVENT
DTSTAMP:20260712T235808Z
UID:tag:localist.com\,2008:EventInstance_42545095086356
DTSTART:20230309T150000Z
DTEND:20230309T160000Z
DESCRIPTION:Abstract: Emerging applications that interact heavily with the 
 physical world (e.g.\, robotics\, medical devices\, the internet of things
 \, augmented and virtual reality\, and machine learning on edge devices) p
 resent critical challenges for modern computer architecture\, including ha
 rd real-time constraints\, strict power budgets\, diverse deployment scena
 rios\, and a critical need for safety\, security\, and reliability. Hardwa
 re acceleration can provide high-performance and energy-efficient computat
 ion\, but design requirements are shaped by the physical characteristics o
 f the target electrical\, biological\, or mechanical deployment\; external
  operating conditions\; application performance demands\; and the constrai
 nts of the size\, weight\, area\, and power allocated to onboard computing
 -- leading to a combinatorial explosion of the computing system design spa
 ce. To address this challenge\, I identify common computational patterns s
 haped by the physical characteristics of the deployment scenario (e.g.\, g
 eometric constraints\, timescales\, physics\, biometrics)\, and distill th
 is real-world information into systematic design flows that span the softw
 are-hardware system stack\, from applications down to circuits. An example
  of this approach is robomorphic computing: a systematic design methodolog
 y that transforms robot morphology into customized accelerator hardware mo
 rphology by leveraging physical robot features such as limb topology and j
 oint type to determine parallelism and matrix sparsity patterns in streaml
 ined linear algebra functional units in the accelerator. Using robomorphic
  computing\, we designed an accelerator for a critical bottleneck in robot
  motion planning and implemented the design on an FPGA for a manipulator a
 rm\, demonstrating significant speedups over state-of-the-art CPU and GPU 
 solutions. Taking a broader view\, in order to design generalized computin
 g systems for robotics and other physically embodied applications\, the tr
 aditional computing system stack must be expanded to enable co-design with
  physical real-world information\, and new methodologies are needed to imp
 lement designs with minimal user intervention. In this talk\, I will discu
 ss my recent work in designing computing systems for robotics\, and outlin
 e a future of systematic co-design of computing systems with the real worl
 d.\n\nBio: Sabrina M. Neuman is a postdoctoral NSF Computing Innovation Fe
 llow at Harvard University. Her research interests are in computer archite
 cture design informed by explicit application-level and domain-specific in
 sights. She is particularly focused on robotics applications because of th
 eir heavy computational demands and potential to improve the well-being of
  individuals in society. She received her S.B.\, M.Eng.\, and Ph.D. from M
 IT. She is a 2021 EECS Rising Star\, and her work on robotics acceleration
  has received Honorable Mention in IEEE Micro Top Picks 2022 and IEEE Micr
 o Top Picks 2023.
GEO:42.444836;-76.482254
LOCATION:Phillips Hall\, 233
SUMMARY:ECE Seminar: Sabrina M. Neuman\, Designing Computing Systems for Ro
 botics and Physically Embodied Deployments
URL;VALUE=URI:https://events.cornell.edu/event/ece_seminar_sabrina_m_neuman
 _designing_computing_systems_for_robotics_and_physically_embodied_deployme
 nts
CATEGORIES:Seminar
END:VEVENT
END:VCALENDAR