Current studentsExisting staffContact us
 

GPBF: A Gaussian Process-Driven Adaptive Barrier Functions for Safety-Critical Control of Quadrotors

Simple item page
dc.contributor.authorLin, Q.
dc.contributor.authorMiao, Z.
dc.contributor.authorWang, X.
dc.contributor.authorHe, W.
dc.contributor.authorWang, Y.
dc.contributor.authorShi, P.
dc.date.issued2025
dc.description.abstractThis article addresses the critical challenge of safe control for quadrotor UAVs operating in environments with unknown disturbances. Existing robust control barrier function methods typically rely on fixed safety boundaries, which are often overly conservative under low uncertainty and insufficiently protective under high uncertainty. To overcome these limitations, we propose a new class of certificates, Gaussian process-based parameterized barrier function (GPBF), which combines learning-based disturbance estimation with adaptive safety constraint design. Specifically, a Gaussian process regression model is employed in a reduced-order model (RoM) to identify and predict disturbances online. The predicted disturbances are used to construct an adaptive parameterized barrier function that dynamically adjusts the safety boundary according to the uncertainty level. In addition, a predictive robust term is derived from iterative full-order model computations and incorporated into the RoM-based GPBF condition to address model discrepancies. The proposed GPBF framework enables real-time adaptation to varying uncertainty levels and dynamic adjustment of safety constraints. Extensive simulations and experimental studies with both single and multiple quadrotors validate the effectiveness of the approach in improving safety guarantees.
dc.description.statementofresponsibilityQiong Lin, Zhiqiang Miao, Xiangke Wang, Wei He, Yaonan Wang, Peng Shi
dc.identifier.citationIEEE Transactions on Aerospace and Electronic Systems, 2025; 61(6):18234-18247
dc.identifier.doi10.1109/TAES.2025.3609755
dc.identifier.issn0018-9251
dc.identifier.issn1557-9603
dc.identifier.orcidShi, P. [0000-0001-6295-0405] [0000-0001-8218-586X] [0000-0002-0864-552X] [0000-0002-1358-2367] [0000-0002-5312-5435]
dc.identifier.urihttps://hdl.handle.net/2440/149351
dc.language.isoen
dc.publisherInstitute of Electrical and Electronics Engineers
dc.relation.granthttp://purl.org/au-research/grants/arc/QL20230097
dc.relation.granthttp://purl.org/au-research/grants/arc/DP240101140
dc.rights© 2025 IEEE
dc.source.urihttps://doi.org/10.1109/taes.2025.3609755
dc.subjectGaussian process regression (GPR); parameterized control barrier functions (CBFs); quadrotors ;reduced order model (ROM); safety-critical control
dc.titleGPBF: A Gaussian Process-Driven Adaptive Barrier Functions for Safety-Critical Control of Quadrotors
dc.typeJournal article
pubs.publication-statusPublished

Files

Collections

Research Outputs