BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Seoul
X-LIC-LOCATION:Asia/Seoul
BEGIN:STANDARD
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
TZNAME:KST
DTSTART:18871231T000000
DTSTART:19881009T020000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20230103T035306Z
LOCATION:Auditorium\, Level 5\, West Wing
DTSTART;TZID=Asia/Seoul:20221206T100000
DTEND;TZID=Asia/Seoul:20221206T120000
UID:siggraphasia_SIGGRAPH Asia 2022_sess153_papers_344@linklings.com
SUMMARY:Asynchronous Collaborative Autoscanning with Mode Switching for Mu
 lti-Robot Scene Reconstruction
DESCRIPTION:Technical Papers\n\nAsynchronous Collaborative Autoscanning wi
 th Mode Switching for Multi-Robot Scene Reconstruction\n\nGuo, Li, Xia, Hu
 , Liu\n\nWhen conducting autonomous scanning for the online reconstruction
  of unknown indoor environments, robots have to be competent at exploring 
 the scene structure and reconstructing objects with high quality. Our key 
 observation is that different tasks demand specialized scanning properties
  of robots: rapid moving speed and far vision for global exploration and s
 low moving speed and narrow vision for local object reconstruction, which 
 are referred as two different scanning modes: scout and raider, respective
 ly. When further requiring multiple robots to collaborate for efficient ex
 ploration and fine-grained reconstruction, we study the questions on when 
 to generate and how to assign those tasks. Therefore, we propose a novel a
 synchronous collaborative autoscanning method with mode switching, which g
 enerates two kinds of scanning tasks with associated scanning modes, i.e.,
  exploration task with scout mode and reconstruction task with raider mode
 , and assign them to the robots to execute in an asynchronous collaborativ
 e manner to highly boost the scanning efficiency and reconstruction qualit
 y. Those generated tasks are assigned to the robots by solving a modified 
 Multi-Depot Multiple Traveling Salesman Problem (MDMTSP). Moreover, to fur
 ther enhance the collaboration and increase the efficiency, we propose a t
 ask-flow model that actives the task generation and assignment process imm
 ediately when any of the robots finishes all its tasks with no need to wai
 t for all other robots to complete the tasks assigned in the previous iter
 ation. Extensive experiments have been conducted to show the importance of
  each key component of our method and the superiority of our method over p
 revious methods in scanning efficiency and reconstruction quality.\n\nRegi
 stration Category: FULL ACCESS, EXPERIENCE PLUS ACCESS, EXPERIENCE ACCESS,
  TRADE EXHIBITOR\n\nLanguage: ENGLISH\n\nFormat: IN-PERSON
URL:https://sa2022.siggraph.org/en/full-program/?id=papers_344&sess=sess15
 3
END:VEVENT
END:VCALENDAR