Recent technological developments have paved the way to the employment of Autonomous Underwater Vehicles (AUVs) for monitoring and exploration activities of marine environments. Traditionally, in information gathering scenarios for monitoring purposes, AUVs follow predefined paths that are not efficient in terms of information content and energy consumption. Informative Path Planning (IPP) represents a valid alternative, defining the path that maximises the gathered information. This work proposes a Genetic Path Planner (GPP), which consists in an IPP strategy based on a Genetic Algorithm, with the aim of generating a path that simultaneously maximises the information gathered and the coverage of the inspected area. The proposed approach has been tested offline for monitoring and inspection applications of Posidonia Oceanica (PO) in three different geographical areas. The a priori knowledge about the presence of PO, in probabilistic terms, has been modelled utilising a Gaussian Process (GP), trained on real marine data. The GP estimate has then been exploited to retrieve an information content of each position in the areas of interest. A comparison with other two IPP approaches has been carried out to assess the performance of the proposed algorithm.
Underwater monitoring activities are crucial for the preservation of marine ecosystems. Currently, scuba divers are involved in data collection campaigns that are repetitive, dangerous, and expensive. This article describes the application of Information Communication Technology (ICT) tools to underwater visual data for monitoring purposes. The data refer to a Posidonia Oceanica survey mission carried out by a scuba diver using a Smart Dive Scooter equipped with visual acquisition and acoustic localization systems. An acoustic-based strategy for geo-referencing of the optical dataset is reported. It exploits the synchronization between the audio track extracted from a camera and the transponder pings adopted for the acoustic positioning. The positioning measurements are employed within an extended Kalman filter to estimate the diver's path during the mission. A visual odometry algorithm is implemented within the filter to refine the navigation state estimation of the diver with respect to the acoustic positioning only. Moreover, a smoothing step based on the Rauch-Tung-Striebel smoother is applied to further improve the estimated diver's positions. Finally, the article reports the results of two different data processing for monitoring applications. The first one is an image mosaicking obtained by concatenating subsequent frames, whereas the second one refers to a qualitative distribution of the Posidonia
Oceanica over the mission area accomplished through an image segmentation process. The two outcomes are plotted over a satellite image of the surveyed area, showing that the proposed process is an effective tool capable of facilitating divers in their monitoring and inspection activities.