Based on known criteria and results for increasing the accuracy of the optimal estimate of the state size of the generalized discrete Kalman filter for nonlinear systems [1], [2], [3] and [5], an adaptive algorithm is proposed in the paper. This algorithm is based on the assumption that the covariance matrix of the measurement disturbance is adaptively adjusted during the implementation of the calculation procedure. The proposed algorithm for increasing the accuracy of optimal or pseudo-optimal estimation can be used in other algorithms for discrete estimation of state variables in nonlinear systems [2] and [4].