Vis enkel innførsel

dc.contributor.authorBøhn, Eivind Eigil
dc.contributor.authorCoates, Erlend Magnus Lervik
dc.contributor.authorMoe, Signe
dc.contributor.authorJohansen, Tor Arne
dc.date.accessioned2020-06-22T10:48:55Z
dc.date.available2020-06-22T10:48:55Z
dc.date.created2019-11-23T12:16:03Z
dc.date.issued2019
dc.identifier.isbn978-1-7281-0333-4
dc.identifier.urihttps://hdl.handle.net/11250/2658999
dc.descriptionPostprint version of published articleen_US
dc.description.abstractContemporary autopilot systems for unmanned aerial vehicles (UAVs) are far more limited in their flight envelope as compared to experienced human pilots, thereby restricting the conditions UAVs can operate in and the types of missions they can accomplish autonomously. This paper proposes a deep reinforcement learning (DRL) controller to handle the nonlinear attitude control problem, enabling extended flight envelopes for fixed-wing UAVs. A proof-of-concept controller using the proximal policy optimization (PPO) algorithm is developed, and is shown to be capable of stabilizing a fixed-wing UAV from a large set of initial conditions to reference roll, pitch and airspeed values. The training process is outlined and key factors for its progression rate are considered, with the most important factor found to be limiting the number of variables in the observation vector, and including values for several previous time steps for these variables. The trained reinforcement learning (RL) controller is compared to a proportional-integral-derivative (PID) controller, and is found to converge in more cases than the PID controller, with comparable performance. Furthermore, the RL controller is shown to generalize well to unseen disturbances in the form of wind and turbulence, even in severe disturbance conditions.en_US
dc.language.isoengen_US
dc.publisherIEEEen_US
dc.relation.ispartof2019 International Conference on Unmanned Aircraft Systems (ICUAS)
dc.subjectUnmanned aerial vehiclesen_US
dc.subjectUAVsen_US
dc.subjectAutopilot systemsen_US
dc.titleDeep Reinforcement Learning Attitude Control of Fixed Wing UAVs Using Proximal Policy Optimizationen_US
dc.typeChapteren_US
dc.typePeer revieweden_US
dc.description.versionacceptedVersionen_US
dc.identifier.cristin1751318
dc.relation.projectNorges forskningsråd: 261791en_US
dc.relation.projectNorges forskningsråd: 272402en_US
dc.relation.projectNorges forskningsråd: 223254en_US
cristin.unitcode7401,90,26,0
cristin.unitnameMathematics and Cybernetics
cristin.ispublishedtrue
cristin.fulltextpostprint
cristin.qualitycode1


Tilhørende fil(er)

Thumbnail

Denne innførselen finnes i følgende samling(er)

Vis enkel innførsel