期刊
ACTA ASTRONAUTICA
卷 214, 期 -, 页码 147-158出版社
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.actaastro.2023.10.018
关键词
Meta-reinforcement learning; Robust trajectory design; Closed-loop guidance; Recurrent neural network; Proximal policy optimization; Stochastic optimal control
This paper explores the application of meta-reinforcement learning in the robust design of low-thrust interplanetary trajectories under multiple uncertainties. It uses a deep recurrent neural network to approximate the control policy and adapts it to different stochastic scenarios through training.
This paper focuses on the application of meta-reinforcement learning to the robust design of low-thrust interplanetary trajectories in the presence of multiple uncertainties. A closed-loop control policy is used to optimally steer the spacecraft to a final target state despite the considered perturbations. The control policy is approximated by a deep recurrent neural network, trained by policy-gradient reinforcement learning on a collection of environments featuring mixed sources of uncertainty, namely dynamic uncertainty and control execution errors. The recurrent network is able to build an internal representation of the distribution of environments, thus better adapting the control to the different stochastic scenarios. The results in terms of optimality, constraint handling, and robustness on a fuel-optimal low-thrust transfer between Earth and Mars are compared with those obtained via a traditional reinforcement learning approach based on a feed-forward neural network.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据