.png){kind=icon}
返回
Collision-aware interactive simulation using graph neural networks
.png){kind=icon}
OA
AI
DOI：10.1186/s42492-022-00113-4.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Deep simulations have gained widespread attention owing to their excellent acceleration performances. However, these methods cannot provide effective collision detection and response strategies. We propose a deep interactive physical simulation framework that can effectively address tool-object collisions. The framework can predict the dynamic information by considering the collision state. In particular, the graph neural network is chosen as the base model, and a collision-aware recursive regression module is introduced to update the network parameters recursively using interpenetration distances calculated from the vertex-face and edge-edge tests. Additionally, a novel self-supervised collision term is introduced to provide a more compact collision response. This study extensively evaluates the proposed method and shows that it effectively reduces interpenetration artifacts while ensuring high simulation efficiency.
Keyword:
Deep physical simulation
Collision-aware
Continuous collision detection
Graph neural network
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
6
论文数:
180
被引数:
702
机构
引用论文
Role of bioinformatics and pharmacogenomics in drug discovery and development process.生物信息学和药物基因组学在药物发现和开发过程中的作用。.png)
IF0
PREAI
分享收藏Genetic variant strains of Leishmania (Viannia) braziliensis exhibit distinct biological behaviors利什曼原虫（维尼亚亚属）巴西利什曼原虫的遗传变异株表现出不同的生物学行为
PREAI
分享收藏Does the fracture fragment at the anterior column in thoracolumbar burst fractures get enough attention?MedicineOAAI
MedicineIF0
OAAI分享收藏Identification of Differentially Expressed Transcripts and Pathways in Blood One Week and Six Months Following Implant of Left Ventricular Assist DevicesPLoS ONEOAAI
PLoS ONEIF0
OAAI分享收藏
查看更多内容