Learning Based Toolpath Planner on Diverse Graphs for 3D Printing

被引:0
作者
Huang, Yuming [1 ]
Guo, Yuhu [1 ]
Su, Renbo [1 ]
Han, Xingjian [2 ]
Ding, Junhao [3 ]
Zhang, Tianyu [1 ]
Liu, Tao [1 ]
Wang, Weiming [1 ]
Fang, Guoxin [3 ]
Song, Xu [3 ]
Whiting, Emily [2 ]
Wang, Charlie c l [1 ]
机构
[1] Univ Manchester, Manchester, England
[2] Boston Univ, Boston, MA USA
[3] Chinese Univ Hong Kong, Hong Kong, Peoples R China
来源
ACM TRANSACTIONS ON GRAPHICS | 2024年 / 43卷 / 06期
关键词
NEURAL-NETWORKS; GAME; GO;
D O I
10.1145/3687933
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
This paper presents a learning based planner for computing optimized 3D printing toolpaths on prescribed graphs, the challenges of which include the varying graph structures on different models and the large scale of nodes & edges on a graph. We adopt an on-the-fly strategy to tackle 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 on 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 method can cover different 3D printing applications by defining their corresponding reward functions. Toolpath planning problems in wire-frame printing, continuous fiber printing, and metallic printing are selected to demonstrate its generality. The performance of our planner has been verified by testing the resultant toolpaths in physical experiments. By using our planner, 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, and the thermal distortion in metallic printing can be reduced by 24.9%. © 2024 Copyright is held by the owner/author(s). Publication rights licensed to ACM.
引用
收藏
页数:16
相关论文
共 53 条
  • [21] Leiserson C.E., 1994, INTRO ALGORITHMS, Vthird
  • [22] Lévy B, 2002, ACM T GRAPHIC, V21, P362, DOI 10.1145/566570.566590
  • [23] Learning Deposition Policies for Fused Multi-Material 3D Printing
    Liao, Kang
    Tricard, Thibault
    Piovarci, Michal
    Seidel, Hans-Peter
    Babaei, Vahid
    [J]. 2023 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2023), 2023, : 12345 - 12352
  • [24] Lillicrap TP, 2015, Continuous control with deep reinforcement learning
  • [25] Path Planning via an Improved DQN-Based Learning Policy
    Lv, Liangheng
    Zhang, Sunjie
    Ding, Derui
    Wang, Yongxiong
    [J]. IEEE ACCESS, 2019, 7 : 67319 - 67330
  • [26] Effects of Set Curvature and Fiber Bundle Size on the Printed Radius of Curvature by a Continuous Carbon Fiber Composite 3D Printer
    Matsuzaki, Ryosuke
    Nakamura, Taishi
    Sugiyama, Kentaro
    Ueda, Masahito
    Todoroki, Akira
    Hirano, Yoshiyasu
    Yamagata, Yusuke
    [J]. ADDITIVE MANUFACTURING, 2018, 24 : 93 - 102
  • [27] Mnih V, 2013, Arxiv, DOI arXiv:1312.5602
  • [28] Human-level control through deep reinforcement learning
    Mnih, Volodymyr
    Kavukcuoglu, Koray
    Silver, David
    Rusu, Andrei A.
    Veness, Joel
    Bellemare, Marc G.
    Graves, Alex
    Riedmiller, Martin
    Fidjeland, Andreas K.
    Ostrovski, Georg
    Petersen, Stig
    Beattie, Charles
    Sadik, Amir
    Antonoglou, Ioannis
    King, Helen
    Kumaran, Dharshan
    Wierstra, Daan
    Legg, Shane
    Hassabis, Demis
    [J]. NATURE, 2015, 518 (7540) : 529 - 533
  • [29] Continuous Eulerian tool path strategies for wire-arc additive manufacturing of rib-web structures with machine-learning-based adaptive void filling
    Nguyen, Lam
    Buhl, Johannes
    Bambach, Markus
    [J]. ADDITIVE MANUFACTURING, 2020, 35
  • [30] A convergent dynamic window approach to obstacle avoidance
    Ögren, P
    Leonard, NE
    [J]. IEEE TRANSACTIONS ON ROBOTICS, 2005, 21 (02) : 188 - 195