Informative path planning with gaussian processes for efficient scalar field reconstruction

Abstract

This paper proposes an adaptive path planning algorithm for efficient scalar field reconstruction with a single vehicle platform. This is done by exploiting the underlying field characteristics so that sampling from the field is more focused on informative areas that leads to a more accurate field reconstruction. To accomplish this, we use Bayesian optimization to optimize sampling locations and Gaussian process regression to model the underlying field. Furthermore, we define a new acquisition function in the Bayesian optimization framework to guide the search for an efficient solution in terms of path length. We compare the proposed method to a commonly used exhaustive coverage path planning algorithm and demonstrate the effectiveness of the proposed approach.