In this paper, we present an unsupervised learning neural model to design transmit precoders for integrated sensing and communication (ISAC) systems to maximize the worst-case target illumination power while ensuring a minimum signal-to-interference-plus-noise ratio (SINR) for all the users. The problem of learning transmit precoders from uplink pilots and echoes can be viewed as a parameterized function estimation problem and we propose to learn this function using a neural network model. To learn the neural network parameters, we develop a novel loss function based on the first-order optimality conditions to incorporate the SINR and power constraints. Through numerical simulations, we demonstrate that the proposed method outperforms traditional optimization-based methods in presence of channel estimation errors while incurring lesser computational complexity and generalizing well across different channel conditions that were not shown during training.

翻译：本文提出了一种无监督学习神经模型，用于设计集成感知与通信（ISAC）系统的发射预编码器，以在确保所有用户满足最小信干噪比（SINR）约束的同时，最大化最差情况下的目标照射功率。从上行导频和回波中学习发射预编码器的问题可视为参数化函数估计问题，我们提出利用神经网络模型来学习该函数。为学习神经网络参数，我们基于一阶最优性条件开发了一种新型损失函数，以融入SINR和功率约束。通过数值仿真，我们证明所提方法在存在信道估计误差时优于传统基于优化的方法，同时具有更低的计算复杂度，并能良好泛化至训练过程中未出现的不同信道条件。