An AUV Adaptive Sampling Path Planning Method Based On Online Model Prediction

摘要

Aiming at the problem of rapid observation of coastal marine environment, an adaptive sampling method based on Gaussian Process Regression (GPR) for small Autonomous Underwater Vehicle (AUV) is proposed. GPR analysis is used to predict the environmental data of unobserved areas based on the realtime observation data from the AUV, and the AUV is guided to implement online path planning by calculating the regional gradient extremes and the forecasting uncertainty. Based on this, an AUV observation direction selection method based on the global estimation of the boundary gravity matrix after data exchange is designed. Finally, this method is used to simulate the regional environmental observation with different feature distributions. Results show that this method can obtain the estimation of low-error feature distribution of the observed area more efficiently than the conventional method, and obtain the hot spot monitor of the observed area more quickly and show more adaptable of the different regional characteristics observation.