In this paper we report an experimental evaluation of three popular methods for online system identification of unmanned surface vehicles (USVs) which were implemented as an ensemble: certifiably stable shallow recurrent neural network (RNN), adaptive identification (AID), and recursive least squares (RLS). The algorithms were deployed on eight USVs for a total of 30 hours of online estimation. During online training the loss function for the RNN was augmented to include a cost for violating a sufficient condition for the RNN to be stable in the sense of contraction stability. Additionally we described an efficient method to calculate the equilibrium points of the RNN and classify the associated stability properties about these points. We found the AID method had lowest mean absolute error in the online prediction setting, but a weighted ensemble had lower error in offline processing.

翻译：本文报告了三种流行的无人水面艇（USV）在线系统辨识方法的实验评估，这些方法以集成方式实现：可证明稳定的浅层循环神经网络（RNN）、自适应辨识（AID）和递归最小二乘（RLS）。该算法部署于八艘USV上，累计进行30小时的在线估计。在线训练过程中，RNN的损失函数被扩展，加入了对违反收缩稳定性意义下RNN稳定性充分条件的惩罚项。此外，我们描述了一种高效计算RNN平衡点的方法，并分类了这些点附近的相关稳定性性质。我们发现，AID方法在在线预测场景中具有最低的平均绝对误差，但在离线处理中，加权集成方法取得了更低的误差。