English NewsSunday, 15 November 2026
Latest
AI

Peer-reviewed optical-fibre sensor applies ResNet–LSTM inference to underwater robot perception

2026-08-16

Peer-reviewed optical-fibre sensor applies ResNet–LSTM inference to underwater robot perception

RoboticsMarine AIPeer reviewedGlobal16 August 2026

Authors: Haiqing Li, Boxue Sun, Xiaonan Bian, Yujia Wang and Xianping Fu. Status: peer-reviewed journal article; performance remains author-reported.

A biomimetic U-shaped plastic optical-fibre sensor uses a cilium-like cantilever to capture orthogonal flow components. A hybrid ResNet–LSTM predicts velocity and direction; the paper reports mean errors of 0.0105 m/s and 1.51°.

Why it matters and impact: The combination of corrosion-resistant sensing and temporal modelling could improve underwater navigation and marine inspection, but field robustness, calibration drift and cross-platform replication remain open.

More AI technology news