BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Personalising Crutch Geometries through Bayesian Optimisation - Ri
 ccardo Conci\, University of Cambridge
DTSTART:20240124T190000Z
DTEND:20240124T200000Z
UID:TALK211480@talks.cam.ac.uk
CONTACT:Pietro Lio
DESCRIPTION:Crutches are optimised for stable motion\, but this safety com
 es at the cost of comfort and speed. In this paper\, we employ Gaussian Pr
 ocesses (GPs) and Bayesian\nOptimisation (BO) as hypothesis generators to 
 find better crutch configurations\, which we validate on a physical protot
 ype. We do so by defining a novel loss function indicating the quality of 
 a crutch design which combines subjective metrics (joint pain\, instabilit
 y and effort) and the corresponding objective ones. Finally\,\nwe (1) use 
 this methodology to build a more stable\, less effortful and less painful 
 personalised crutch design and (2) use the knowledge built by the GP throu
 gh these\nexperiments to enhance our understanding of the physical dynamic
 s of crutching.
LOCATION:Lecture Theatre 2\, Computer Laboratory\, William Gates Building
END:VEVENT
END:VCALENDAR