Multi-maneuvering target tracking method based on depth deterministic strategy gradient DDPG

Abstract

The invention belongs to the field of target tracking, and particularly relates to a multi-maneuvering target tracking method based on a depth deterministic strategy gradient DDPG. The method includes: establishing a depth deterministic strategy gradient network; generating deep deterministic strategy gradient network input data sk by using an LSTM network; setting actions and returns of the depthdeterministic strategy gradient network to obtain a set depth deterministic strategy gradient network; training the set depth deterministic strategy gradient network according to the depth deterministic strategy gradient network input data sk to obtain a trained depth deterministic strategy gradient network; and performing multi-maneuvering target tracking by using the trained depth deterministicstrategy gradient network. The method is reasonable in resource distribution and high in radar tracking precision, and the problems of no model and Markov decision are solved.

Description

technical field [0001] The invention belongs to the field of target tracking, and in particular relates to a multi-maneuvering target tracking method based on deep deterministic policy gradient DDPG. Background technique [0002] The main task of multi-maneuvering target tracking technology is to allocate enough radar resources to each maneuvering target to achieve the expected tracking accuracy under the condition of limited radar resources. In practical applications, limited by the total power of radar transmission and the number of targets to be tracked, it is necessary to allocate resources to each target reasonably. The traditional method of evenly allocating radar resources to each target will cause the problem of decreased tracking accuracy. At present, a lot of work has been devoted to using cognitive technology to allocate radar resources to improve target tracking accuracy. However, these methods either rely on the estimation of the motion model of the target, or ...

AI Technical Summary

Problems solved by technology

This method only considers the tracking accuracy at the next moment when the target is irradiated each time, and does not consider the impact of this allocation result on the target tracking performance in the future.

Images