Target tracking in Interference Environments reinforcement learning and design for cognitive radar soft processing

For target tracking in Interference Environments of cognitive radar problem, Extended Karman, Particle filter algorithms etc. are generally used to be regarded as usual solutions to state estimation. Many techniques have been developed to improve performance of target tracking. In this paper, we set the structure and key features of target's tracking design for cognitive radar, and newly propose cognitive tracking filter algorithm based on the VS multiple models PF (VS-MMPF), Elman NN and the group methods for data processing (GMDH). The cognitive tracking algorithm is capable of solving the accuracy of the estimation around the likely points. We applied the proposed algorithm to the cognitive radar tracking problems especially emphasis on reinforcement learning, choice of algorithms, recognizing severe circumstances and information preservation. Simulation results showed that the design of cognitive tracking had superior performance on the accuracy and robust of tracking, compared with the general approaches.