Robotic Active Information Gathering for Spatial Field Reconstruction with Rapidly-Exploring Random Trees and Online Learning of Gaussian Processes

Abstract

Information gathering (IG) algorithms aim to intelligently select a mobile sensor actions required to efficiently obtain an accurate reconstruction of a physical process, such as an occupancy map, or a magnetic field. Many recent works have proposed algorithms for IG that employ Gaussian processes (GPs) as underlying model of the process. However, most algorithms discretize the state space, which makes them computationally intractable for robotic systems with complex dynamics. Moreover, they are not suited for online information gathering tasks as they assume prior knowledge about GP parameters. This paper presents a novel approach that tackles the two aforementioned issues. Specifically, our approach includes two intertwined steps: (i) a Rapidly-Exploring Random Tree (RRT) search that allows a robot to identify unvisited locations, and to learn the GP parameters, and (ii) an RRT*-based informative path planning that guides the robot towards those locations by maximizing the information gathered while minimizing path cost. The combination of the two steps allows an online realization of the algorithm, while eliminating the need for discretization. We demonstrate that our proposed algorithm outperforms state-of-the-art both in simulations, and in a lab experiment in which a ground-based robot explores the magnetic field intensity within an indoor environment populated with obstacles.

An Integrated Strategy for Autonomous Exploration of Spatial Processes in Unknown Environments

“…Ideas similar to active mapping can be used to explore the spatial field [8]. However, this can lead to potentially conflicting goals, given that different models and sensors (with a different FOV, etc.)…”

“…Recent advances in mobile robotics have opened new frontiers for the development of novel exploration algorithms. In the literature, approaches for robot exploration are typically based on the maximum informativeness criterion (e.g., [8,[10][11][12]), which guides the robot towards locations with the highest information gain.…”

“…Informative sampling that takes into account an information metric (i.e., mutual information that takes into account statistical dependencies between sampling point candidates) in combination with GPs has been considered for different exploration applications, e.g., magnetic field mapping [8], environmental monitoring [13], and online estimation of a radio signal source [14]. However, the works in [8,13,14] assume the environment in which the robot operates as a priori known. In order to deploy autonomous robots in complex environments, we must develop algorithms that are able to operate in unknown environments.…”

Distributed Multi-Robot Information Gathering under Spatio-Temporal Inter-Robot Constraints

“…Informative path planning techniques typically encompass algorithms that aim to plan a path which is both feasible, given a robot's dynamical constraints, and optimal with respect to some information quality metric. Single-robot approaches for informative path planning in continuous spaces have been proposed in [15][16][17][18][19][20]. However there is little work in the literature that propose multi-robot informative path planning algorithms.…”

Rapidly-Exploring Adaptive Sampling Tree*: A Sample-Based Path-Planning Algorithm for Unmanned Marine Vehicles Information Gathering in Variable Ocean Environments

“…Sample-based algorithms, such as rapidly-exploring random tree (RRT) [24], probabilistic roadmap (PRM) [25], and variants of them, with the advantage of generating a collision-free path quickly in continuous space, have been studied extensively in the past years. Rapidly-exploring random tree star (RRT*) [26], a variant of standard RRT, is guaranteed asymptotic optimality and has been widely used for solving the path planning problem [27][28][29][30][31]. Therefore, RRT* can be an alternative choice to be employed in the informative path planning problem for adaptive sampling.…”