Indirect detection phase control algorithms, such as the dithering algorithm and the stochastic parallel gradient descent algorithm (SPGD), have simple system structures and are applicable to filled-aperture coherent combinations with high efficiency. The performances of these algorithms are limited when applied to a coherent combination of pulsed fiber lasers with a low repetition rate (≤5 kHz). Firstly, due to the overlap of the phase noise frequency and repetition rate, conventional algorithms cannot effectively distinguish the phase noise from the pulse fluctuation, and directly applying filtering will result in the phase information being filtered out. Secondly, if the pulse fluctuation is ignored and only the continuous part of the phase information is utilized, it relies on the presetting of conditions to separate the pulse from the continuous part and loses the phase information of the pulse part. In this article, we propose a waveform self-referencing algorithm (WSRA) based on a two-channel near-infrared laser coherent combination system to overcome the above challenges. Firstly, by modelling a self-referencing waveform, a nonlinear scaling operation is performed on the combined signal to generate a pseudo-continuous signal, which removes the intrinsic pulse fluctuation while preserving the phase noise information. Secondly, the phase control signal is calculated based on the pseudo-continuous signals after parallel perturbation. Finally, the phase noise is corrected by optimization. The results show that our method effectively suppresses the waveform fluctuation at a 5 kHz repetition rate, the light intensity reaches an ideal value (0.9939 $I_{\max }$), and the root-mean-square (RMS) phase error is only 0.0130 $\lambda$. This method does not require the presetting of pulse detection thresholds or conditions, and solves the challenge of coherent combination at a low repetition rate, with adaptability to different pulse waveforms.

This paper presents a novel free-space optical Angle-of-Arrival (AOA) estimation method based on arrayed waveguide coherent mode decoding, aiming to surpass the inherent limitations of traditional AOA detection technologies, which face significant challenges in achieving miniaturization, low complexity, and high reliability. The method utilizes the AOA-related phase differences generated by the propagation and interference of incident light in an arrayed input waveguide, forming multi-beam interference fringes at the output end of the slab waveguide. This pattern is then sampled by an arrayed output waveguide to produce an intensity sequence, which is then fed into a trained CNN–Attention Regressor for AOA estimation. This study innovatively applies the method to decoding the spatial angular information of optical signals. Simulation results demonstrate the exceptional performance of our approach, achieving a Mean Absolute Error (MAE) of 0.0142° and a Root Mean Square Error (RMSE) of 0.0193° over a 40° field of view. This precision is significantly superior to conventional peak–linear calibration methods and other common neural network architectures, and exhibits remarkable robustness against simulated phase noise and manufacturing tolerances. This research demonstrates the powerful synergy between integrated photonics and deep learning, paving the way for a new class of highly integrated, robust, and high-performance on-chip optical sensors.