IEEE Trans Neural Netw Learn Syst. 2019 Nov;30(11):3370-3383. doi: 10.1109/TNNLS.2019.2891257. Epub 2019 Jan 31.
In this paper, we address the state initialization problem in recurrent neural networks (RNNs), which seeks proper values for the RNN initial states at the beginning of a prediction interval. The proposed methods employ various forms of neural networks (NNs) to generate proper initial state values for RNNs. A variety of RNNs are trained using the proposed NN initialization schemes for modeling two aerial vehicles, a helicopter and a quadrotor, from experimental data. It is shown that the RNN initialized by the NN-based initialization method outperforms the washout method which is commonly used to initialize RNNs. Furthermore, a comprehensive study of RNNs trained for multistep prediction of the two aerial vehicles is presented. The multistep prediction of the quadrotor is enhanced using a hybrid model, which combines a simplified physics-based motion model of the vehicle with RNNs. While the maximum translational and rotational velocities in the Quadrotor data set are about 4 m/s and 3.8 rad/s, respectively, the hybrid model produces predictions, over 1.9 s, which remain within 9 cm/s and 0.12 rad/s of the measured translational and rotational velocities, with 99% confidence on the test data set.
在本文中，我们解决了递归神经网络（RNN）中的状态初始化问题，即在预测区间开始时为 RNN 的初始状态寻找合适的值。所提出的方法使用各种形式的神经网络（NN）为 RNN 生成合适的初始状态值。使用所提出的 NN 初始化方案对两种飞行器，直升机和四旋翼飞行器的实验数据进行了多种 RNN 的训练。结果表明，由基于 NN 的初始化方法初始化的 RNN 优于通常用于初始化 RNN 的冲洗方法。此外，还对用于两种飞行器多步预测的 RNN 进行了全面研究。使用混合模型增强了四旋翼飞行器的多步预测，该模型将车辆的简化基于物理的运动模型与 RNN 相结合。虽然 Quadrotor 数据集的最大平移和旋转速度分别约为 4 m/s 和 3.8 rad/s，但混合模型在 1.9 秒以上的预测中，平移和旋转速度仍保持在测量值的 9 cm/s 和 0.12 rad/s 以内，在测试数据集上的置信度为 99%。
