In the adaptive optics (AO) system, to improve the effectiveness and accuracy of wavefront sensing-less technology, a phase-based sensing approach using machine learning is proposed. In contrast to the traditional gradient-based optimization methods, the model we designed is based on an improved convolutional neural network. Specifically, the deconvolution layer, which reconstructs unknown input by measuring output, is introduced to represent the phase maps of the point spread functions at the in focus and defocus planes. The improved convolutional neural network is utilized to establish the nonlinear mapping between the input point spread functions and the corresponding phase maps of the optical system. Once well trained, the model can directly output the aberration map of the optical system with good precision. Adequate simulations and experiments are introduced to demonstrate the accuracy and real-time performance of the proposed method. The simulations show that even when atmospheric conditions D/r₀ = 20, the detection root-mean-square of wavefront error of the proposed method is 0.1307 λ, which has a better accuracy than existing neural networks. When D/r₀ = 15 and 10, the root-mean-square error is respectively 0.0909 λ and 0.0718 λ. It has certain applicative value in the case of medium and weak turbulence. The root-mean-square error of experiment results with D/r₀ = 20 is 0.1304 λ, proving the correctness of simulations. Moreover, this method only needs 12 ms to accomplish the calculation and it has broad prospects for real-time wavefront sensing.

In this paper, an improved method of measuring wavefront aberration based on image with machine learning is proposed. This method had better real-time performance and higher estimation accuracy in free space optical communication in cases of strong atmospheric turbulence. We demonstrated that the network we optimized could use the point spread functions (PSFs) at a defocused plane to calculate the corresponding Zernike coefficients accurately. The computation time of the network was about 6–7 ms and the root-mean-square (RMS) wavefront error (WFE) between reconstruction and input was, on average, within 0.1263 waves in the situation of D/r0 = 20 in simulation, where D was the telescope diameter and r0 was the atmospheric coherent length. Adequate simulations and experiments were carried out to indicate the effectiveness and accuracy of the proposed method.

This article focuses on a beacon-less Inter-satellite optical wireless communication (Is-OWC) system. This system uses the same wavelength for the transmitted and received laser beams and uses part of communication light beam as beacon light instead of an additional high divergent beacon laser. Thus, a part of transmitted light will be reflected in optical path and leaked into acquisition, tracking and targeting (ATP) subsystem. This reflected light will seriously interfere with the spot position measurement of received light. To solve this problem, we propose a new method based on intensity modulation and cyclic cross-correlation (CCR). Experiment results show that even when the reflected and received beams differ in intensity by 91.7 times, we can still accurately detect the received light spot position by using the proposed method, where the maximum error is 0.026 mrad and the root mean square error is as low as 0.012 mrad.

The image-based piston sensing method using the convolutional neural network (CNN) is an advanced technique which has good applicability. However, acquiring a large amount of the training dataset required to train a network is difficult to handle in practice. In this letter, we demonstrate the possibility of using a neural network trained by the simulation dataset to accurately sense pistons directly from experimental images. As a demonstration of the proposed scheme, a single CNN developed by computer-generated images is applied for piston measurement of an experimental setup with three sub-apertures. This is particularly helpful for the sparse aperture system with more sub-apertures. We believe that the study in this letter will contribute to the applications of the CNN-based technique for piston sensing.

Inter-satellite laser communication (Is-OWC) is one of the main space optical communication technologies currently studied in various countries. In recent years, a kind of Is-OWC communication terminal without independent beacon light has appeared. Such terminals do not have a separate beacon laser with a large divergence angle, but use a narrower communication beam to complete space capture and tracking. Therefore, the energy of the light beam divided by the acquisition, tracking, and aiming (ATP) system is greatly reduced. How to perform high-precision spot position detection under extremely low signal-to-noise ratio (SNR) is a problem that must be faced. Aiming to resolve this problem, this article proposes to use a cosine signal to modulate the intensity of the signal light, so as to convert the problem of detecting a weak light signal into the problem of detecting a line spectrum signal. The authors used the time reversal convolution (TRC) algorithm with a window function to suppress noise and enhance the spectrum line, so as to accurately detect the amplitudes of the weak photocurrents. Finally, by calculating the ratio of the photocurrent amplitude values, the precise spot position is obtained. In the experiment, when the output SNR of the four-quadrant detector (QD) is as low as −17.86 dB, the proposed method can still detect the spot position and the absolute error is limited within 0.0238 mrad.