Wind Based Navigation for Zero-Pressure Stratospheric Balloons Using Reinforcement learning

Document identifier: oai:DiVA.org:ltu-76542
Keyword: Engineering and Technology, Teknik och teknologier, Reinforcement learning, Balloon, Stratospheric winds, Onboard space systems, Rymdtekniska system
Publication year: 2019
Relevant Sustainable Development Goals (SDGs):

The SDG label(s) above have been assigned by OSDG.ai

Abstract:

The horizontal motion of the balloon is governed by the winds at the float altitude. In order to navigate, and change the direction of balloon flight, knowledge of the wind environment around the balloon is needed. The real time navigation and control of zero-pressure balloons is a challenging task as there are no sensors that can be used onboard the balloon to provide real knowledge of the wind environment. Further, their is no active actuation possible and the resources available for passive actuation are limited. These constraints makes the balloon flight difficult and inflexible. In this paper, a solution to this problem of balloon navigation, and its path planning is presented by using data from ECMWF in combination with reinforcement learning. Data from ECMWF gives an overview of almost real-time environment and a reinforcement learning algorithm help in optimizing the passive actuation resources.

Authors

Kanika Garg

Luleå tekniska universitet; Rymdteknik
Other publications >>

Record metadata

Click to view metadata

	
    header: 
        identifier: oai:DiVA.org:ltu-76542
        datestamp: 2021-04-19T12:36:14Z
        setSpec: SwePub-ltu
    metadata: 
        mods: 
            @attributes: 
                version: 3.7
            recordInfo: 
                recordContentSource: ltu
                recordCreationDate: 2019-10-28
            identifier: http://urn.kb.se/resolve?urn=urn:nbn:se:ltu:diva-76542
            titleInfo: 
                @attributes: 
                    lang: eng
                title: Wind Based Navigation for Zero-Pressure Stratospheric Balloons Using Reinforcement learning
            abstract: 
The horizontal motion of the balloon is governed by the winds at the float altitude. In order to navigate and change the direction of balloon flight knowledge of the wind environment around the balloon is needed. The real time navigation and control of zero-pressure balloons is a challenging task as there are no sensors that can be used onboard the balloon to provide real knowledge of the wind environment. Further their is no active actuation possible and the resources available for passive actuation are limited. These constraints makes the balloon flight difficult and inflexible. In this paper a solution to this problem of balloon navigation and its path planning is presented by using data from ECMWF in combination with reinforcement learning. Data from ECMWF gives an overview of almost real-time environment and a reinforcement learning algorithm help in optimizing the passive actuation resources.

            subject: 
                    @attributes: 
                        lang: eng
                        authority: uka.se
                    topic: Engineering and Technology
                    @attributes: 
                        lang: swe
                        authority: uka.se
                    topic: Teknik och teknologier
                    @attributes: 
                        lang: eng
                    topic: Reinforcement learning
                    @attributes: 
                        lang: eng
                    topic: balloon
                    @attributes: 
                        lang: eng
                    topic: Stratospheric winds
                    @attributes: 
                        lang: eng
                        authority: ltu
                    topic: Onboard space systems
                    genre: Research subject
                    @attributes: 
                        lang: swe
                        authority: ltu
                    topic: Rymdtekniska system
                    genre: Research subject
            language: 
                languageTerm: eng
            genre: 
                publication/journal-article
                ref
            note: 
                Submitted
                1
            name: 
                @attributes: 
                    type: personal
                    authority: ltu
                namePart: 
                    Garg
                    Kanika
                role: 
                    roleTerm: aut
                affiliation: 
                    Luleå tekniska universitet
                    Rymdteknik
                nameIdentifier: kangar
            relatedItem: 
                    @attributes: 
                        type: host
                    genre: grantAgreement
                    name: 
                        @attributes: 
                            type: corporate
                        namePart: Rymdstyrelsen
                        role: 
                            roleTerm: fnd
                    identifier: 3941025
                    @attributes: 
                        type: host
                    titleInfo: 
                        title: Acta Astronomica
                    identifier: 0001-5237
            originInfo: 
                dateIssued: 2019
            physicalDescription: 
                form: print
            typeOfResource: text