Sensor?driven autonomous underwater inspections: A receding?horizon RRT?based view planning solution for AUVs

Autonomous Underwater Vehicles (AUVs) are used by the scientific community for various applications, from collecting well-distributed high-quality data to mapping seafloor or exploring unknown areas. Nonpredictable environmental conditions and sensor acquisitions make design of AUV surveys challenging even expert operators. Multiple attempts required, collected quality is not guaranteed: The passively stores sensors' that then analyzed offline after its recovery. In Forward-Looking SONAR (FLS) seabed inspections, vehicle follows lawnmower paths designed an operator considers characteristics. performance FLSs affected several possible protruding objects. This paper presents a probabilistic framework FLS-based inspections endow with ability autonomously conducting survey ensure adequate coverage target area. A three-dimensional occupancy system FLS reconstructions update covered area map was developed. Coverage Path Planning (CPP) algorithm evaluate visibility viewpoints generated as nodes random tree. Next-Best Viewpoint (NBV) selected first node in branch expected collect more data, path reach NBV computed using rapidly tree (RRT*) algorithm. sensor-driven approach receding-horizon manner. proposed Receding-Horizon Approach validated simulations real prerecorded data. Finally, online during experimental campaign where were performed.