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

Alberto Viseras, Dmitriy Shutin, and Luis Merino. Robotic Active Information Gathering for Spatial Field Reconstruction with Rapidly-Exploring Random Trees and Online Learning of Gaussian Processes. Sensors, 19(6):, MDPI, 2019.

Download

[PDF] [html] 

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 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 GPs 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 GPs 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 of 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.

BibTeX Entry

@ARTICLE{sensors19ipp,
year={2019},
issn={1424-8220},
journal={Sensors},
volume = {19},
number = {6},
title={{Robotic Active Information Gathering for Spatial Field Reconstruction with Rapidly-Exploring Random Trees and Online Learning of Gaussian Processes}},
publisher={MDPI},
author={Alberto Viseras and Dmitriy Shutin and Luis Merino},
pages={},
doi = {10.3390/s19051016},
  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 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 GPs 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 GPs  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 of 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.},
}

Generated by bib2html.pl (written by Patrick Riley ) on Fri Oct 04, 2019 13:12:53