Information Processing and Telecommunications Center, E.T.S. Ingenieros de Telecomunicación, Universidad Politécnica de Madrid, 28040 Madrid, Spain.
Sensors (Basel). 2021 Jul 23;21(15):5011. doi: 10.3390/s21155011.
We use the recent advances in Deep Learning to solve an underwater motion planning problem by making use of optimal control tools-namely, we propose using the Deep Galerkin Method (DGM) to approximate the Hamilton-Jacobi-Bellman PDE that can be used to solve continuous time and state optimal control problems. In order to make our approach more realistic, we consider that there are disturbances in the underwater medium that affect the trajectory of the autonomous vehicle. After adapting DGM by making use of a surrogate approach, our results show that our method is able to efficiently solve the proposed problem, providing large improvements over a baseline control in terms of costs, especially in the case in which the disturbances effects are more significant.
我们利用深度学习的最新进展，通过利用最优控制工具来解决水下运动规划问题，即我们提出使用深度伽辽金方法（DGM）来近似可以用于解决连续时间和状态最优控制问题的哈密顿-雅可比-贝尔曼偏微分方程。为了使我们的方法更符合实际情况，我们考虑到水下介质存在干扰，会影响自动驾驶车辆的轨迹。在利用替代方法对 DGM 进行适配后，我们的结果表明，我们的方法能够有效地解决所提出的问题，在成本方面，尤其是在干扰影响更显著的情况下，相对于基线控制提供了很大的改进。
