Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Multi-Task Oriented Semantic Communication Framework for Autonomous Vehicles

Eslam Eldeeb, Mohammad Shehab, Hirley Alves

TL;DR

Simulation results show that the proposed framework outperforms the conventional schemes, such as QAM-16, regarding the reconstructed image’s similarity and the classification’s accuracy, and can save up to 89% of the bandwidth by sending fewer bits.

Abstract

Task-oriented semantic communication is an emerging technology that transmits only the relevant semantics of a message instead of the whole message to achieve a specific task. It reduces latency, compresses the data, and is more robust in low SNR scenarios. This work presents a multi-task-oriented semantic communication framework for connected and autonomous vehicles (CAVs). We propose a convolutional autoencoder (CAE) that performs the semantic encoding of the road traffic signs. These encoded images are then transmitted from one CAV to another CAV through satellite in challenging weather conditions where visibility is impaired. In addition, we propose task-oriented semantic decoders for image reconstruction and classification tasks. Simulation results show that the proposed framework outperforms the conventional schemes, such as QAM-16, regarding the reconstructed image's similarity and the classification's accuracy. In addition, it can save up to 89 % of the bandwidth by sending fewer bits.

A Multi-Task Oriented Semantic Communication Framework for Autonomous Vehicles

TL;DR

Simulation results show that the proposed framework outperforms the conventional schemes, such as QAM-16, regarding the reconstructed image’s similarity and the classification’s accuracy, and can save up to 89% of the bandwidth by sending fewer bits.

Abstract

Task-oriented semantic communication is an emerging technology that transmits only the relevant semantics of a message instead of the whole message to achieve a specific task. It reduces latency, compresses the data, and is more robust in low SNR scenarios. This work presents a multi-task-oriented semantic communication framework for connected and autonomous vehicles (CAVs). We propose a convolutional autoencoder (CAE) that performs the semantic encoding of the road traffic signs. These encoded images are then transmitted from one CAV to another CAV through satellite in challenging weather conditions where visibility is impaired. In addition, we propose task-oriented semantic decoders for image reconstruction and classification tasks. Simulation results show that the proposed framework outperforms the conventional schemes, such as QAM-16, regarding the reconstructed image's similarity and the classification's accuracy. In addition, it can save up to 89 % of the bandwidth by sending fewer bits.
Paper Structure (7 sections, 7 equations, 4 figures, 1 table, 1 algorithm)

This paper contains 7 sections, 7 equations, 4 figures, 1 table, 1 algorithm.

Table of Contents

  1. Introduction
  2. System model and Problem Formulation
  3. The Multi-Task Semantic Framework
  4. Numerical Results and Discussion
  5. Image Classification
  6. Image Reconstruction
  7. Conclusions

Figures (4)

  • Figure 1: (a) Road sign with impaired visibility, (b) The proposed multi-task semantic communication framework.
  • Figure 2: The classification accuracy of the proposed algorithm compared to the conventional schemes, the confusion matrix and the classification report of testing the semantic model at $P_t = 15 \: dBm$ and a codeword of $64$.
  • Figure 3: The SSIM of the proposed algorithm compared to the conventional schemes and the total transmitted bytes.
  • Figure 4: Some examples of reconstructed images using different transmission schemes. The first row shows the original images. The second row shows the reconstructed images using the proposed model at $P_t = 15 \: dBm$ and a codeword of $64$. The bottom row shows the reconstructed images using JPEG+QAM 16.