BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Optimizing Robotic Systems at All Scales
DTSTART:20251202T160000
DTEND:20251202T170000
DTSTAMP:20260407T111522Z
UID:8e40f78e1851a9d5663ae6094f75f6c926a626a549104a8e4bb3b4a8
CATEGORIES:Conferences - Seminars
DESCRIPTION:Assistant Professor Brian K. Plancher\, Computer Science at D
 artmouth College\, USA.\nAbstract:\nIntelligent field robots are a promisi
 ng solution to many societal challenges from combating epidemics\, to scal
 ing global supply chains\, to providing home health care to the elderly. H
 owever\, today\, robots are mostly limited to laboratory settings as the c
 omputational intensity of many robotics algorithms prevents their real-tim
 e use on edge robotic hardware. In this talk\, I will discuss how my lab i
 s addressing these challenges through algorithm-hardware-software co-desig
 n\, generating new algorithms and implementations that can run at real-tim
 e rates on the edge. Specifically\, I will show how the performance of non
 linear model predictive control (MPC) algorithms can be significantly enha
 nced through a combination of parallelism\, approximation\, numerical cond
 itioning\, and structure exploitation. Through the resulting theoretical a
 nd computational advancements\, our work has enabled GPU-accelerated whole
 -body nonlinear MPC for manipulators at kHz rates over long-horizon trajec
 tories\, as well as real-time dynamic obstacle avoidance for microcontroll
 er-powered tiny quadrotors. This work sets the stage for a future filled w
 ith dynamic\, adaptable\, and useful robotic systems.\n\nBio:\nBrian Planc
 her is an Assistant Professor of Computer Science at Dartmouth College whe
 re he leads the Accessible and Accelerated Robotics Lab (A²R Lab). He was
  previously an Assistant Professor of Computer Science at Barnard College 
 where he also held affiliate positions in Computer Science and Electrical 
 Engineering at Columbia University. He received his A.B.\, M.Eng.\, and Ph
 .D. from Harvard University. Brian is also a co-chair for the Tiny Machine
  Learning Open Education Initiative (TinyMLedu) and an associate co-chair 
 for the IEEE-RAS TC on Model Based Optimization for Robotics.
LOCATION:ME C2 405 https://plan.epfl.ch/?room==ME%20C2%20405
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR