Analytic dynamic models for target estimation are often approximations of the potentially complex behaviour of the object of interest. Its true motion might depend on hundreds of parameters and can involve long-term temporal correlation. However, conventional models keep the degrees of freedom low and they usually assume the Markov property to reduce computational complexity. In particular, the Kalman Filter assumes prior and posterior Gaussian densities and is hence restricted to linear transition functions which are often insufficient to reflect the behaviour of a real object. In this letter, a Mnemonic Kalman Filter is introduced which overcomes the Markov property and the linearity restriction by learning to predict a full transition probability density with Long Short-Term Memory networks.

中文翻译：

---

具有广泛时间依赖性的非线性系统的助记卡尔曼滤波器

用于目标估计的分析动态模型通常是感兴趣对象潜在复杂行为的近似值。它的真实运动可能取决于数百个参数，并且可能涉及长期时间相关性。然而，传统模型保持较低的自由度，并且它们通常假设马尔可夫性质以降低计算复杂度。特别是，卡尔曼滤波器假定先验和后验高斯密度，因此仅限于线性转换函数，这些函数通常不足以反映真实对象的行为。在这封信中，介绍了一种助记符卡尔曼滤波器，它通过学习使用长短期记忆网络预测完整的转移概率密度来克服马尔可夫特性和线性限制。