Cubature Kalman Filter

The cubature Kalman filter (CKF) is the closest approximation known so far to the Bayesian filter that could be designed in a nonlinear setting under the Gaussian assumption. Unlike the extended Kalman filter (EKF), CKF does not require evaluation of Jacobians during the estimation process, while in EKF the nonlinear functions are approximated by their Jacobians, the first-order Taylor’s series approximation.