.png){kind=icon}
返回
Finding Optimal Paths Using Networks Without Learning--Unifying Classical Approaches
.png){kind=icon}
OA
AI
DOI：10.1109/TNNLS.2021.3089023.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Trajectory or path planning is a fundamental issue in a wide variety of applications. In this article, we show that it is possible to solve path planning on a maze for multiple start point and endpoint highly efficiently with a novel configuration of multilayer networks that use only weighted pooling operations, for which no network training is needed. These networks create solutions, which are identical to those from classical algorithms such as breadth-first search (BFS), Dijkstra's algorithm, or TD(0). Different from competing approaches, very large mazes containing almost one billion nodes with dense obstacle configuration and several thousand importance-weighted path endpoints can this way be solved quickly in a single pass on parallel hardware.
Keyword:
Nonhomogeneous media
Transforms
Reinforcement learning
Planning
Network architecture
Measurement
Heuristic algorithms
Deep multilayer network
multiagent systems
multisource shortest paths
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:
8.9
论文数:
7.6K
被引数:
7.2W
机构
引用论文
Does it take older adults longer than younger adults to perceptually segregate a speech target from a background masker?在感知上将语音目标与背景掩蔽器隔离开来是否需要老年人比年轻人更长的时间？
PREAI
分享收藏Comparative study of thermally conductive fillers in underfill for the electronic components电子元件底层填料中导热填料的比较研究
PREAI
分享收藏分享收藏Guanidine-based polycarbonate hydrogels: from metal-free ring-opening polymerization to reversible self-assembling properties.png)
Soft Matter
Soft MatterIF0
PREAI
分享收藏
查看更多内容