26 September 2024 in IEEE Network
Expected to provide higher transportation efficiency and security, autonomous driving has attracted substantial attentions from both industry and academia. Meanwhile, the emergence of edge intelligence has further introduced significant advancements to this field. However, the crucial demands of ultra-reliable and low-latency communications (URLLC) among the vehicles and edge servers have hindered the development of autonomous driving. In this article, we provide a brief overview of edge intelligence enabled autonomous driving system and current vehicle-to-everything (V2X) technologies. Moreover, challenges associated with massive data transmission in autonomous driving are highlighted from three perspectives: multi-modal data transmission and fusion, multi-user collaboration and connection, and multi-task training and execution. To cope with these challenges, we propose to incorporate semantic communication into autonomous driving to achieve highly efficient and task-oriented data transmission. Unlike traditional communications, semantic communication extracts task-relevant semantic feature from multi-sensory data. Specifically, a unified multi-user semantic communication system for transmitting multi-modal data and performing multi-task execution is designed for collaborative data transmission and decision making in autonomous driving. Simulation results demonstrate that the proposed system can significantly reduce data transmission volume without compromising task performance, as evidenced by the realization of a cooperative multi-vehicle target classification and detection task.
23 January 2025 in IEEE Transactions on Cognitive Communications and Networking
Semantic communication (SemCom) based image transmission schemes, in contrast to conventional bit-based schemes, achieve a substantial reduction in transmission data volume while maintaining superior image quality under conditions of limited data due to their inherent robustness against channel noise.However, most existing SemCom systems are based on analog communication paradigms, allowing for the transmission of arbitrary complex values over the channel. The analog communication model may lead to incompatibility with digital commercial hardware and standardized protocols.In this paper, we propose an end-to-end digital SemCom system with a learnable channel estimator (DiSeLCE) aligning with the constraints of digital communication systems. Specifically, we first design a novel semantic encoder and decoder that integrate dense blocks to enhance feature extraction and significantly reduce the number of model parameters.Moreover, we employ a soft-to-hard quantization method to effectively mitigate the discontinuity in the model gradient due to quantization mappings.Furthermore, both the domain knowledge and residual network (ResNet) are leveraged to develop a learnable channel estimation model, further enhancing the robustness of the proposed system in frequency-selective fading channels for orthogonal frequency-division multiplexing (OFDM) transmission. Experimental results demonstrate that the proposed DiSeLCE performs well under frequency-selective fading channels, facilitating efficient image transmission even under low signal-to-noise ratios (SNR) conditions. Furthermore, DiSeLCE exhibits robust generalization capabilities across different types of datasets.
29 May 2024 in IEEE Internet of Things Journal
As the number of users connected to communication networks, such as cellular networks and Internet of Things (IoT) networks increases, massive multiple-input-multiple-output (MIMO) technique has been widely adopted to improve the spectral and energy efficiency. However, the multiuser frequency synchronization problem must be solved before channel estimation and data detection. Concurrent estimation of multiple carrier frequency offsets (CFOs) at base station could be very challenging due to the coexisting and intertwined effects of multiple CFOs and uplink channels in the received signal. In this article, we consider the frequency synchronization and channel estimation for multiuser uplink massive MIMO systems. To solve the complex multi-CFO estimation problem, we first derive the efficient joint multiuser frequency synchronization algorithm based on the maximum likelihood (ML) criterion, whose high-computational complexity is reduced by the proposed Gauss-Newton method. Furthermore, we develop a multistage iteration update filtering (MIUF)-based multiuser CFO and channel estimation method. The least squares (LSs) algorithm is adopted to estimate the channels, based on which the filtering matrix is carefully designed to perform multiuser interference (MUI) suppression. Moreover, considering the effect of CFO error on the channel estimation, an iterative procedure is designed to improve MUI suppression and estimation accuracy. We also analyze the CFO estimation performance and obtain the theoretical expression of mean squared error (MSE). Finally, the effect of CFO error on channel estimation is derived. Numerical results are provided to corroborate the effectiveness of the proposed methods and their superiority over the existing ones.