Active planning for underwater inspection and the benefit of adaptivity

Abstract

We discuss the problem of inspecting an underwater structure, such as a submerged ship hull, with an autonomous underwater vehicle (AUV). Unlike a large body of prior work, we focus on planning the views of the AUV to improve the quality of the inspection, rather than maximizing the accuracy of a given data stream. We formulate the inspection planning problem as an extension to Bayesian active learning, and we show connections to recent theoretical guarantees in this area. We rigorously analyze the benefit of adaptive re-planning for such problems, and we prove that the potential benefit of adaptivity can be reduced from exponential to a constant factor by changing the problem from cost minimization with a constraint on information gain to variance reduction with a constraint on cost. Such analysis allows the use of robust, nonadaptive planning algorithms that perform competitively with adaptive algorithms. Based on our analysis, we propose a method for constructing 3D meshes from sonar-derived point clouds, and we introduce uncertainty modeling through non-parametric Bayesian regression. Finally, we demonstrate the benefit of active inspection planning using sonar data from ship hull inspections with the Bluefin-MIT Hovering AUV.

Laser-Radar Data Fusion with Gaussian Process Implicit Surfaces

“…A framework to estimate IS surfaces with uncertainties using Gaussian Process, named GPIS, has been proposed in the literature. This approach has been applied to range sensor data for robotics applications in different contexts, such as change detection [14], active learning [6], and grasping [8].…”

“…{m.castro,t.peynot,f.ramos}@acfr.usyd.edu.au come the aforementioned problems. Firstly, the generated model is fully predictive as it is able to predict a surface at arbitrary regions of an object that were not entirely observed by the range sensor [6]. Secondly, the model also yields the uncertainty of the estimates, at any point of the surface.…”

Adaptive informative path planning in metric spaces

“…The importance and the difficulty in obtaining optimal solutions for IPP have attracted significant interest in recent years. One idea is to choose a set of "informative" sensing locations and then construct a minimum-cost tour to traverse them [11]. Another idea is to search for a plan over a finite horizon [10].…”

Exploring Underwater Environments with Curiosity

“…Das et al [8] have presented techniques to autonomously observe oceanographic features in the open ocean. Hollinger et al [16] have studied the problem of autonomously studying underwater ship hulls by maximizing the accuracy of sonar data stream. Smith et al [26] have looked at computing robot trajectories which maximize information gained, while minimizing the deviation from the planned path.…”