BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Date iCal//NONSGML kigkonsult.se iCalcreator 2.20.2//
METHOD:PUBLISH
X-WR-CALNAME;VALUE=TEXT:Eventi DIAG
BEGIN:VTIMEZONE
TZID:Europe/Paris
BEGIN:STANDARD
DTSTART:20251026T030000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
RDATE:20261025T030000
TZNAME:CET
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20260329T020000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:calendar.30670.field_data.0@www.diag.uniroma1.it
DTSTAMP:20260529T223404Z
CREATED:20260421T132906Z
DESCRIPTION:  Abstract:In this talk\, I will present my research on enhanci
 ng robotic motion and control across diverse and challenging scenarios.Fir
 st\, I will explore the generation of optimal jumping motions using Reinfo
 rcement Learning (RL)\, integrating physical insights to guide the learnin
 g process.This significantly reduces the training time compared to standar
 d end-to-end approaches.Second\, I will illustrate the development of nove
 l robotic platforms that combine ropes and legged systems to address the c
 hallenges of maintenance in remote\, hazardous environments. By leveraging
  optimal control techniques\, I designed a computationally efficient plann
 ing algorithm for precise and adaptive jumping motions.  
DTSTART;TZID=Europe/Paris:20260428T150000
DTEND;TZID=Europe/Paris:20260428T150000
LAST-MODIFIED:20260526T083425Z
LOCATION:Aula A6 - DIAG
SUMMARY:Avviso di Sminario 'Aerial motions for legged robots' - Prof. Miche
 le Focchi
URL;TYPE=URI:https://www.diag.uniroma1.it/node/30670
END:VEVENT
END:VCALENDAR