Online Multi-modal Learning and Adaptive Informative Trajectory Planning for Autonomous Exploration

Arora, A; Furlong, PM; Fitch, R; Fong, T; Sukkarieh, S; Elphic, R

Online Multi-modal Learning and Adaptive Informative Trajectory Planning for Autonomous Exploration

Arora, A Furlong, PM Fitch, R

Fong, T Sukkarieh, S Elphic, R

Permalink

Publisher:: Springer International Publishing
Publication Type:: Conference Proceeding
Citation:: Field and Service Robotics, 2018, pp. 239 - 254
Issue Date:: 2018

Closed Access

	Filename	Description	Size
	FSR_2017_paper_28.pdf	Accepted Manuscript version	1.58 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Arora, A	en_US
dc.contributor.author	Furlong, PM	en_US
dc.contributor.author	Fitch, R https://orcid.org/0000-0003-2215-5188	en_US
dc.contributor.author	Fong, T	en_US
dc.contributor.author	Sukkarieh, S	en_US
dc.contributor.author	Elphic, R	en_US
dc.contributor.editor	Hutter, M	en_US
dc.contributor.editor	Siegwart, R	en_US
dc.date	2017-09-12	en_US
dc.date.issued	2018	en_US
dc.identifier.citation	Field and Service Robotics, 2018, pp. 239 - 254	en_US
dc.identifier.isbn	978-3-319-67360-8	en_US
dc.identifier.issn	2511-1256	en_US
dc.identifier.uri	http://hdl.handle.net/10453/127742
dc.description.abstract	In robotic information gathering missions, scientists are typically interested in understanding variables which require proxy measurements from specialized sensor suites to estimate. However, energy and time constraints limit how often these sensors can be used in a mission. Robots are also equipped with cheaper to use navigation sensors such as cameras. In this paper, we explore a challenging planning problem in which a robot is required to learn about a scientific variable of interest in an initially unknown environment by planning informative paths and deciding when and where to use its sensors. To tackle this we present two innovations: a Bayesian generative model framework to automatically learn correlations between expensive science sensors and cheaper to use navigation sensors online, and a sampling based approach to plan for multiple sensors while handling long horizons and budget constraints. Our approach does not grow in complexity with data and is anytime making it highly applicable to field robotics. We tested our approach extensively in simulation and validated it with real data collected during the 2014 Mojave Volatiles Prospector Mission. Our planning algorithm performs statistically significantly better than myopic approaches and at least as well as a coverage-based algorithm in an initially unknown environment while having added advantages of being able to exploit prior knowledge and handle other intricacies of the real world without further algorithmic modifications.	en_US
dc.publisher	Springer International Publishing	en_US
dc.relation.ispartof	Field and Service Robotics	en_US
dc.relation.isbasedon	10.1007/978-3-319-67361-5_16	en_US
dc.title	Online Multi-modal Learning and Adaptive Informative Trajectory Planning for Autonomous Exploration	en_US
dc.type	Conference Proceeding
utslib.location	Germany	en_US
utslib.location.activity	Zurich, Switzerland	en_US
utslib.for	0913 Mechanical Engineering	en_US
utslib.for	0906 Electrical and Electronic Engineering	en_US
pubs.embargo.period	Not known	en_US
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Strength - CAS - Centre for Autonomous Systems
utslib.copyright.status	closed_access
pubs.consider-herdc	false	en_US
pubs.finish-date	2017-09-15	en_US
pubs.place-of-publication	Germany	en_US
pubs.start-date	2017-09-12	en_US

Abstract:

In robotic information gathering missions, scientists are typically interested in understanding variables which require proxy measurements from specialized sensor suites to estimate. However, energy and time constraints limit how often these sensors can be used in a mission. Robots are also equipped with cheaper to use navigation sensors such as cameras. In this paper, we explore a challenging planning problem in which a robot is required to learn about a scientific variable of interest in an initially unknown environment by planning informative paths and deciding when and where to use its sensors. To tackle this we present two innovations: a Bayesian generative model framework to automatically learn correlations between expensive science sensors and cheaper to use navigation sensors online, and a sampling based approach to plan for multiple sensors while handling long horizons and budget constraints. Our approach does not grow in complexity with data and is anytime making it highly applicable to field robotics. We tested our approach extensively in simulation and validated it with real data collected during the 2014 Mojave Volatiles Prospector Mission. Our planning algorithm performs statistically significantly better than myopic approaches and at least as well as a coverage-based algorithm in an initially unknown environment while having added advantages of being able to exploit prior knowledge and handle other intricacies of the real world without further algorithmic modifications.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/127742