Multisensors Fusion for Trajectory Tracking Based on Variational Normalizing Flow

The problem of multisensors fusion target trajectory tracking under the Bayesian variational inference (VI) is to find the jointly accurate posterior distribution. In this article, a joint optimization method, called VINFNet, combining inference modeling and data-driven is proposed. The proposed VINFNet incorporates the respective advantages of state-space latent inference models and deep generative network that can explicitly model the physical process of target motion and construct complex posterior distributions of target trajectory through a series of invertible mappings. Specifically, the joint probabilistic representation of the multisensors latent variable is generated by VI, with the optimization on the evidence lower bound (ELBO) to guarantee convergence. However, finding the approximate posterior distribution of targets in VI is a crucially intractable problem. Therefore, a normalized flow generation model under a multilayers perceptron strategy is proposed to recover the approximate posterior distribution of targets, overcoming the challenge of choosing the posterior distribution during VI. The proposed VINFNet neither requires the computation of complex Jacobi matrices as in model-based algorithms such as Kalman filter (KF) nor lacks interpretability as in data-driven neural networks. Simulations and ablation experiments evaluate that the VINFNet algorithm outperforms prevalent methods regarding convergence, accuracy, robustness, and effectiveness via fusing different data sources.