Combination of IMM Algorithm and ASTRWCKF for Maneuvering Target Tracking

Abstract

In this paper, an improved interactive multiple model adaptive strong tracking random weighted cubature Kalman filter (IIMM-ASTRWCKF) algorithm is developed to overcome the low tracking accuracy and easy divergence when dealing with complex maneuvering situations. The algorithm is improved in two aspects: On the one hand, ASTRWCKF is used as the sub filter of IMM algorithm to filter different motion models. By introducing the random weight factor to replace the original weight factor, the accuracy of the algorithm is improved. At the same time, the adaptive strong tracking filter is added to update the prediction covariance matrix and noise covariance matrix for the stability of the algorithm. On the other hand, this algorithm proposes a new method to improve the probability conversion accuracy of IMM by adding time-varying factor to adjust Markov probability transfer matrix. Compared with the performance of IMM-CKF and in dealing with maneuvering problems, IIMM-ASTRWCKF algorithm has better tracking accuracy in solving maneuvering problem.

Multiple adaptive factors based interacting multiple model estimator

“…To validate the effectiveness of the proposed method, this section conducts simulations on the following seven robust state estimators: (1) the proposed multiple adaptive factors based interacting multiple model estimator (MAFIMME), (2) the original robust state estimator (RE), (3) the robust estimators with MR adaptive factor (MRRE), ( 4) the robust estimators with Huber adaptive factor (HRE), ( 5) the robust estimators with RMA adaptive factor (RMARE), ( 6) the robust estimators with Mahalanobis adaptive factor (MRE) and ( 7) the adaptive strong tracking cubature Kalman filter (ASTCKF) [22]. The simulation details and parameter descriptions are provided as follows:…”

“…One primary method to address the unpredictable increase in observation noise involves introducing adaptive factors. This entails assessing and adjusting the estimation error covariance, process noise covariance, and observation noise covariance based on residuals to enhance estimation accuracy [21][22][23]. The adaptive strong tracking cubature Kalman filter (ASTCKF) method proposed in [22] accomplishes corrections to all three, thereby enhancing estimator performance.…”

“…This entails assessing and adjusting the estimation error covariance, process noise covariance, and observation noise covariance based on residuals to enhance estimation accuracy [21][22][23]. The adaptive strong tracking cubature Kalman filter (ASTCKF) method proposed in [22] accomplishes corrections to all three, thereby enhancing estimator performance. However, it relies on an accurate motion model and does not meet the robustness requirements of optoelectronic tracking scenarios.…”

Noise-Adaption Extended Kalman Filter Based on Deep Deterministic Policy Gradient for Maneuvering Targets

“…To implement higher tracking accuracy for the maneuvering target tracking, many improved strong tracking cubature Kalman filter (STCKF), such as strong tracking spherical simplex-radial CKF [ 28 ], fifth-degree STCKF [ 29 ], Bayesian-based strong tracking interpolatory CKF [ 30 ], model-based strong tracking square-root CKF [ 31 ], have recently been proposed. In addition, Ma et al [ 32 ] added STF into the sub-filter of IMM to overcome the low tracking accuracy when dealing with maneuvering situations. However, in practical applications, it is found that the detection and tracking ability of the STF method will be reduced when the maneuver of the target is small.…”