BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:IC Colloquium : Designing Processors to Accelerate Robot Motion Pl
 anning
DTSTART:20171030T161500
DTEND:20171030T173000
DTSTAMP:20260407T002633Z
UID:8a6f81ee5a76ff11fbfab9336b7ebccc66c13862e9fc3bca7f338a50
CATEGORIES:Conferences - Seminars
DESCRIPTION:By : Daniel Sorin - Duke University\n\nAbstract :\nWe have dev
 eloped a hardware accelerator for motion planning\, a critical operation i
 n robotics. I will  present the microarchitecture of our accelerator and 
 describe a prototype implementation on an FPGA. Experimental results show 
 that\, compared to the state of the art\, the accelerator improves perform
 ance by three orders of magnitude and improves power consumption by more t
 han one order of magnitude. These gains are achieved through careful hardw
 are/software co-design. We have modified conventional motion planning algo
 rithms to aggressively precompute collision data\, and we have implemented
  a microarchitecture that leverages the parallelism present in the problem
 .\n\nBio :\nDaniel J. Sorin is the Addy Professor of Electrical and Comput
 er Engineering at Duke University.  His research interests are in compute
 r architecture\, with a focus on fault tolerance\, verification\, and memo
 ry system design.  He is the author of "Fault Tolerant Computer Architect
 ure" and a co-author of "A Primer on Memory Consistency and Cache Coherenc
 e."  He is the recipient of a SICSA Distinguished Visiting Fellowship\, a
  National Science Foundation Career Award\, and Duke's Imhoff Distinguishe
 d Teaching Award.  He received a PhD and MS in electrical and computer en
 gineering from the University of Wisconsin\, and he received a BSE in elec
 trical engineering from Duke University.\n\nMore information\n 
LOCATION:BC 420 https://plan.epfl.ch/?room==BC%20420
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR