BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.sciwork.dev//seminar26//ZXHZQC
BEGIN:VTIMEZONE
TZID:Asia/Taipei
BEGIN:STANDARD
DTSTART:20000101T000000
RRULE:FREQ=YEARLY;BYMONTH=1
TZNAME:CST
TZOFFSETFROM:+0800
TZOFFSETTO:+0800
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-seminar26-AJMNA7@pretalx.sciwork.dev
DTSTART;TZID=Asia/Taipei:20260613T111000
DTEND;TZID=Asia/Taipei:20260613T114000
DESCRIPTION:This talk introduces the basic ideas behind quadrotor optimal c
 ontrol and reinforcement learning from a practical\, beginner-friendly per
 spective. We will discuss how position\, velocity\, attitude\, and angular
  velocity are used to describe the drone state\, and how a controller conv
 erts tracking errors into motor commands.\n\nSeveral representative contro
 l approaches will be introduced\, including the Linear Quadratic Regulator
  (LQR)\, H∞ robust control\, Model Predictive Control (MPC)\, and Reinfo
 rcement Learning (RL). The talk will explain the intuition behind each met
 hod: what it tries to optimize\, what kinds of problems it handles well\, 
 and what trade-offs appear in practice.\n\nThe examples will be based on R
 otorBench\, an open-source Python-based quadrotor control benchmarking fra
 mework. More details about the project are available at: https://github.co
 m/shengwen-tw/rotor-bench
DTSTAMP:20260726T123157Z
LOCATION:R115
SUMMARY:From Optimal Control to Reinforcement Learning for Quadrotor Drones
  - Sheng-Wen Cheng
URL:https://pretalx.sciwork.dev/seminar26/talk/AJMNA7/
END:VEVENT
END:VCALENDAR