arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.11332astro-ph.IMastro-ph.EPcs.LG
收藏

基于强化学习的高对比度成像自优化自适应光学控制

Self-optimizing adaptive optics control with Reinforcement Learning for high-contrast imaging

Leiden Observatory, Leiden University(莱顿大学莱顿天文台)

Rico Landman, Sebastiaan Y. Haffert, Vikram M. Radhakrishnan, Christoph U. Keller

摘要:

目前和未来的高对比度成像仪器需要极端的自适应光学(XAO)系统,以达到直接成像系外行星所需的对比度。望远镜的振动和由控制回路的延迟引起的时间误差限制了这些系统的性能。减少这些影响的一种方法是使用预测控制。我们描述了无模型强化学习如何用于优化闭环预测控制的递归神经网络控制器。首先,我们验证了我们提出的方法在模拟和实验室设置的倾斜倾斜控制。结果表明,该算法可以有效地学习,以减轻振动和减少的残差幂律输入湍流相比,最佳增益积分器。我们还表明,控制器可以学习,以尽量减少随机振动,而不需要在线更新的控制律。接下来,我们在模拟中表明,我们的算法也可以应用到高阶变形镜的控制。我们证明,我们的控制器可以提供两个数量级的改善对比度在小的分离下,稳定的湍流。此外,我们显示了一个以上的数量级的改善,对比不同的风速和方向,而不需要在线更新的控制律。

英文摘要:

Current and future high-contrast imaging instruments require extreme adaptive optics (XAO) systems to reach contrasts necessary to directly image exoplanets. Telescope vibrations and the temporal error induced by the latency of the control loop limit the performance of these systems. One way to reduce these effects is to use predictive control. We describe how model-free Reinforcement Learning can be used to optimize a Recurrent Neural Network controller for closed-loop predictive control. First, we verify our proposed approach for tip-tilt control in simulations and a lab setup. The results show that this algorithm can effectively learn to mitigate vibrations and reduce the residuals for power-law input turbulence as compared to an optimal gain integrator. We also show that the controller can learn to minimize random vibrations without requiring online updating of the control law. Next, we show in simulations that our algorithm can also be applied to the control of a high-order deformable mirror. We demonstrate that our controller can provide two orders of magnitude improvement in contrast at small separations under stationary turbulence. Furthermore, we show more than an order of magnitude improvement in contrast for different wind velocities and directions without requiring online updating of the control law.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑