Target-aware Informative Path Planning and semantic occupancy mapping for AUV autonomous inspections

This paper introduces an innovative methodology for enabling AUVs to explore an area of interest while simultaneously look for and localize OPIs. A probabilistic semantic occupancy mapping solution that fuses an FLS-based mapping solution and a CNN-based ATR strategy has been designed. In detail. it permits to includes the knowledge about the presence of the OPIs by using the ATR findings. The semantic map enables the Informative Path Planning algorithm to generate paths that cover the area of interest and simultaneously reduces the target localization uncertainty. Therefore, this methodology allows an AUV to meaningfully perceive and model the solution surroundings and autonomously conduct inspections surveys. The proposed solution has been validated with realistic simulations made by means of the Unmanned Underwater Vehicle Simulator, where a dynamic model of FeelHippo AUV was implemented.