Efficient reacquire and identify path planning over large areas

Abstract

Abstract-An important task in maritime search and inspection involves re-acquiring and identifying underwater objects by surveying the objects from multiple angles. Because of false contacts related to clutter on the sea floor, the objects are often detected in dramatically different densities in a given area. Previously developed methods to plan survey paths on groups of contacts led to efficient paths when the contacts occur in close proximity, but inefficient paths when the objects occur over large distances. We present a planning algorithm to generate an efficient path to survey objects from multiple angles that is independent of the density of the objects. The algorithm leverages the previously-developed algorithms for surveying objects from multiple directions, coupled with density-based spatial clustering of applications with noise (DBSCAN) clustering and ant colony optimization techniques.

Informative Multiview Planning for Underwater Sensors

“…The IMVP approach developed in this article is tested on a variety of target fields and compared to the state-of-the-art multiview planning methods known as MAC and clustered MAC (CMAC) [1], [2], [38], [69], [70]. Because the objects' locations and features used for classification all influence the UUV-based sensor performance, the IMVP approach is demonstrated first by considering different object layouts (Section VII-A) and, then, different classification sets (Section VII-B) using the simulation environment described in Section VI.…”

“…The MAC path may be inefficient for sparse object layouts, requiring the UUV-based sensor to travel long times without observing any objects [1], [38], [69], [70]. The modification proposed in [2], known as CMAC, overcomes this limitation by designing the path based on the size of object clusters that may occur in applications with man-made TOIs [71], [72]. Objects are first grouped in clusters by using density-based spatial clustering of applications with noise method and, then, the shortest path between clusters is found, typically reducing travel time compared to MAC solutions.…”

“…Previous multiview planning studies showed that path performance depends strongly on the object layout [1], [2], [38], [69], [70]. In particular, algorithms that perform well for objects uniformly distributed spatially, at random, over the ROI may not perform adequately when objects are laid out into clusters, and viceversa.…”

“…Multiple aspect coverage (MAC) and adaptive MAC algorithms have been developed to solve multiview path planning problems by first generating a star-like path around every target and, then, computing the shortest route between them [1], [2]. MAC-type algorithms rely on the user choosing the number of views required for every target, and, subsequently, picking a subset of vehicle-heading angles by sampling uniformly the 180 • range of all possible angles.…”

“…), three target fields are generated by sampling n = 19 underwater objects from sets A, B, and C. The corresponding IMVP trajectories, respectively, plotted in2 Percent improvement over best existing algorithm.…”