Predicting the Motion of a USV Using Support Vector Regression with Mixed Kernel Function

Xu, Pengfei; Cao, Qingbo; Shen, Yalin; Chen, Meiya; Ding, Yanxu; Cheng, Hong

doi:10.3390/jmse10121899

Cited by 4 publications

(1 citation statement)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, other filtering methods [27] are also considered as integrated navigation filters. Moreover, some studies have proposed using artificial intelligence methods to assist GNSS/ INS integrated navigation when GNSS signals are interrupted [28]. In the same time interval, under the premise of ensuring that they are not overwhelmed by noise, the navigation results of INS and GNSS should have a certain correlation for USV.…”

Section: Introductionmentioning

confidence: 99%

A robust integrated navigation optimization method for USV in signal occlusion environment

Lou,

Liu,

et al. 2024

Phys. Scr.

View full text Add to dashboard Cite

Unmanned surface vehicles (USV) can use global navigation satellite systems (GNSS) and inertial navigation systems (INS) for combined positioning and navigation. However, buildings such as port facilities and bridges blocking GNSS signals will increase the error in the discriminator output in the GNSS vector tracking loop and reduce positioning accuracy. Meanwhile, due to the cumulative error in the inertial navigation system, the credibility of the navigation results when the signal is blocked is further reduced. In this regard, this study proposes a robust integrated navigation optimization method. Specifically, the RTS smoothing optimized Kalman filter is used to constrain the carrier phase error and code phase error output by the discriminator, which can dynamically adjust the gain of the vector tracking loop, thereby improving the signal tracking capability. Simultaneously, the prediction results of the gated recurrent unit (GRU) network optimized based on the attention mechanism are combined with the inertial navigation system to improve navigation accuracy. Furthermore, an adaptive Kalman filter is utilized as the integrated navigation filter. The actual path of the carrier refers to the navigation solution of the existing receiver. In the open environment, the proposed optimization method reduces horizontal positioning error and speed error by 44.7% and 37.1% respectively compared with existing methods. Simultaneously, it can effectively improve the robustness of positioning in signal obstruction environments. The proposed integrated navigation method provides new possibilities for optimizing USV navigation solutions.

show abstract

Section: Introductionmentioning

confidence: 99%

A robust integrated navigation optimization method for USV in signal occlusion environment

Lou,

Liu,

et al. 2024

Phys. Scr.

View full text Add to dashboard Cite

show abstract

Appraising the crop health response to water stress from enhanced crop and soil water estimates using SAR data and machine learning approaches

Gopi

Periasamy

2023

International Journal of Remote Sensing

View full text Add to dashboard Cite

Post-Processing Maritime Wind Forecasts from the European Centre for Medium-Range Weather Forecasts around the Korean Peninsula Using Support Vector Regression and Principal Component Analysis

Moon,

Kim,

Kim

2024

JMSE

View full text Add to dashboard Cite

Accurate wind data are crucial for successful search and rescue (SAR) operations on the sea surface in maritime accidents, as survivors or debris tend to drift with the wind. As maritime accidents frequently occur outside the range of wind stations, SAR operations heavily rely on wind forecasts generated by numerical models. However, numerical models encounter delays in generating results due to spin-up issues, and their predictions can sometimes exhibit inherent biases caused by geographical factors. To overcome these limitations, we reviewed the observations for the first 24 h of the 72-hour forecast from the ECMWF and then post-processed the forecast for the remaining 48 h. By effectively reducing the dimensionality of input variables comprising observation and forecast data using principal component analysis, we improved wind predictions with support vector regression. Our model achieved an average RMSE improvement of 16.01% compared to the original forecast from the ECMWF. Furthermore, it achieved an average RMSE improvement of 5.42% for locations without observation data by employing a model trained on data from the nearest wind station and then applying an adaptive weighting scheme to the output of that model.

show abstract

Predicting the Motion of a USV Using Support Vector Regression with Mixed Kernel Function

Cited by 4 publications

References 15 publications

A robust integrated navigation optimization method for USV in signal occlusion environment

A robust integrated navigation optimization method for USV in signal occlusion environment

Appraising the crop health response to water stress from enhanced crop and soil water estimates using SAR data and machine learning approaches

Post-Processing Maritime Wind Forecasts from the European Centre for Medium-Range Weather Forecasts around the Korean Peninsula Using Support Vector Regression and Principal Component Analysis

Contact Info

Product

Resources

About