wireless communication hardware

时序状态融合自适应跟踪控制网络

Temporal-state fusion adaptive tracking control network

A neural network architecture designed to jointly process consecutive spot images, inter-frame differences, and structured motion states to improve the reliability of tracking fragmented spots caused by atmospheric turbulence. / 一种神经网络架构，旨在联合处理连续光斑图像、帧间差异和结构化运动状态，以提高由大气湍流引起的碎片化光斑跟踪的可靠性。

Knowledge type: 工艺技术
First proposed or discovered: 2026
Proposer: Xiangyu Feng, Haifeng Yao, Youyi Wang, Liang Tang, Kexin Miao, Weihao Wang, Tong Zhang, Wenxuan Cheng
Creator: 农场主
Last updated: 2026-11-03 16:05:56

Sub-knowledge points

Motion-enhanced temporal perceptionVision-state reliability gatingMulti-task prediction headsSpot-center localizationMotion-trend estimationObservation reliability assessmentDegradation-level discriminationControl-correction prediction

Higher-order knowledge points

No connected node yet

Main parameters and performance indicators

MPE (Mean Pointing Error): 0.91 µ radRMSE (Root-Mean-Square Error): 8.57 µ radTATC-Net: The proposed network architecture

Open problems

No unresolved problem recorded yet

Related literature

ranked by community stars

Stable tracking of turbulence-disturbed laser communication spots using a time-series state fusion networkOpen source

时序状态融合自适应跟踪控制网络

Sub-knowledge points

Higher-order knowledge points

Main parameters and performance indicators

Open problems

Related products and links