Bayesian transfer learning is added to UKF and CKF so that parameters from a low-noise source sensor improve estimates in a high-noise primary sensor, with simulations showing better performance than isolated filters or measurement fusion.
Approximations to optimal nonlinear filters
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.SY 1years
2024 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Object Tracking Incorporating Transfer Learning into Unscented and Cubature Kalman Filters
Bayesian transfer learning is added to UKF and CKF so that parameters from a low-noise source sensor improve estimates in a high-noise primary sensor, with simulations showing better performance than isolated filters or measurement fusion.