BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Tokyo
X-LIC-LOCATION:Asia/Tokyo
BEGIN:STANDARD
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
TZNAME:JST
DTSTART:18871231T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20250110T023312Z
LOCATION:Hall B5 (1)\, B Block\, Level 5
DTSTART;TZID=Asia/Tokyo:20241205T105900
DTEND;TZID=Asia/Tokyo:20241205T111300
UID:siggraphasia_SIGGRAPH Asia 2024_sess127_papers_533@linklings.com
SUMMARY:Learning Based Toolpath Planner on Diverse Graphs for 3D Printing
DESCRIPTION:Technical Papers\n\nYuming Huang, Yuhu Guo, and Renbo Su (Univ
 ersity of Manchester); Xingjian Han (Boston University); Junhao Ding (Chin
 ese University of Hong Kong); Tianyu Zhang, Tao Liu, and Weiming Wang (Uni
 versity of Manchester); Guoxin Fang and Xu Song (Chinese University of Hon
 g Kong); Emily Whiting (Boston University); and Charlie Wang (University o
 f Manchester)\n\nThis paper presents a learning based planner for computin
 g optimized 3D printing toolpaths on prescribed graphs, the challenges of 
 which include the varying graph structures on different models and the lar
 ge scale of nodes & edges on a graph. We adopt an on-the-fly strategy to t
 ackle these challenges, formulating the planner as a Deep Q-Network (DQN) 
 based optimizer to decide the next `best' node to visit. We construct the 
 state spaces by the Local Search Graph (LSG) centered at different nodes o
 n a graph, which is encoded by a carefully designed algorithm so that LSGs
  in similar configurations can be identified to re-use the earlier learned
  DQN priors for accelerating the computation of toolpath planning. Our met
 hod can cover different 3D printing applications by defining their corresp
 onding reward functions. Toolpath planning problems in wire-frame printing
 , continuous fiber printing, and metallic printing are selected to demonst
 rate its generality. The performance of our planner has been verified by t
 esting the resultant toolpaths in physical experiments. By using our plann
 er, wire-frame models with up to 4.2k struts can be successfully printed, 
 up to 93.3% of sharp turns on continuous fiber toolpaths can be avoided, a
 nd the thermal distortion in metallic printing can be reduced by 24.9%.\n\
 nRegistration Category: Full Access, Full Access Supporter\n\nLanguage For
 mat: English Language\n\nSession Chair: Lin Lu (Shandong University)
URL:https://asia.siggraph.org/2024/program/?id=papers_533&sess=sess127
END:VEVENT
END:VCALENDAR