Learning-based Predictive Beamforming for Integrated Sensing and Communication in Vehicular Networks

Abstract

This paper investigates the integrated sensing and communication (ISAC) in vehicle-to-infrastructure (V2I) networks. To realize ISAC, an effective beamforming design is essential which however, highly depends on the availability of accurate channel tracking requiring large training overhead and computational complexity. Motivated by this, we adopt a deep learning (DL) approach to implicitly learn the features of historical channels and directly predict the beamforming matrix to be adopted for the next time slot to maximize the average achievable sum-rate of an ISAC system. The proposed method can bypass the need of explicit channel tracking process and reduce the signaling overhead significantly. To this end, a general sum-rate maximization problem with Cramer-Rao lower bounds (CRLBs)-based sensing constraints is first formulated for the considered ISAC system. Then, by exploiting the penalty method, a versatile unsupervised DL-based predictive beamforming design framework is developed to address the formulated design problem. As a realization of the developed framework, a historical channelsbased convolutional long short-term memory (LSTM) network (HCL-Net) is devised for predictive beamforming in the ISAC-based V2I network. Specifically, the convolution and LSTM modules are successively adopted in the proposed HCL-Net to exploit the spatial and temporal dependencies of communication channels to further improve the learning performance. Finally, simulation results show that the proposed predictive method not only guarantees the required sensing performance, but also achieves a satisfactory sum-rate that can approach the upper bound obtained by the genie-aided scheme with the perfect instantaneous channel state information.

Time-Frequency Mask Aware Bi-directional LSTM: A Deep Learning Approach for Underwater Acoustic Signal Separation

“…Input and reference label processing: First, randomly take [2 C] underwater acoustic audio files from the file library and mix them according to equation (20). Each audio file needs to be averaged before entering the network training:…”

“…At present, this method has been used to solve image recognition, natural language processing (NLP) and even communication problems [19]. Deep learning approach [20]- [23] also makes a breakthrough in the separation of signals. Therefore, we extract the features of the underwater acoustic signals by means of deep learning approach.…”

End-to-End Learning for Integrated Sensing and Communication

“…The literature on joint waveforms for ISAC includes (i) communication waveforms used for sensing, e.g., [11], [18]; (ii) sensing waveforms used for communication, e.g., [19], [20]; and (iii) flexible designs that offer a trade-off between communication or sensing [5], [21]- [29]. Existing approaches in the latter category differ in terms of the ISAC objective function (e.g., radar and communication information rates [5], weighted radar peak-to-sidelobe level and communication signal-to-noise ratio (SNR) [21], transmit power with interference constraints [22], radar SNR under communication similarity constraint [23], generalized radar metrics under communication error constraints [24], communication interference subject to a communication similarity constraint [25], radar Cramér-Rao bound (CRB) under rate constraints [26], communication rate under CRB [27] and radar similarity [29] constraints) and the ISAC optimization variables (e.g., power [5], [29], signal covariance [21], beamformers [22], [24], [26], [27], transmit sequences across antennas [23], [25], weighted multibeams [28]).…”

“…Since the optimization problem in joint waveform design is often non-convex, approximate solution techniques are often applied, including those based on machine learning (ML) [27]. Data-driven ML methods are also useful under model deficits, e.g., to mitigate effects of array calibration errors, mutual coupling, power amplifier nonlinearity, quantization effects etc., which are expected to be prevalent in 6G [9].…”