Reservoir Computing for Drone Trajectory Intent Prediction: A Physics Informed Approach
提出一种物理信息储备池计算方案，结合标准储备池计算和非线性控制反馈，提升无人机异常轨迹预测的准确性和鲁棒性，并用李雅普诺夫理论验证算法收敛性。
The design of accurate trajectory prediction algorithms is crucial to implement adequate countermeasures against drones with anomalous performances. Wrong predictions may cause high-false-positives that compromise safety in national infrastructures. In this article, a physics informed reservoir computing (PIRC) scheme for drone trajectory prediction is proposed. The approach is comprised of two main complementary learning algorithms that enhance the prediction and generalization capabilities: 1) a standard reservoir computing scheme for high-dimensional encoding exploitation and 2) a nonlinear control scheme that gives a physical feedback to the reservoir weights to ensure the prediction error is minimized. The nonlinear control scheme is modeled by the prediction error dynamics and a feedback linearization controller. Two different PIRC schemes are proposed which preserve the reservoir properties and enhance the prediction robustness. Lyapunov stability theory is used to verify the boundedness and convergence of the proposed algorithms. Simulation studies and comparisons are given to verify the proposed approach.