A Multi-Task Oriented Semantic Communication Framework for Autonomous Vehicles
This work addresses bandwidth and reliability challenges for autonomous vehicle communication in adverse conditions, though it is incremental as it builds on existing semantic communication methods.
The paper tackles the problem of transmitting road traffic sign information between connected autonomous vehicles in low-visibility weather by proposing a multi-task semantic communication framework that uses a convolutional autoencoder for encoding and task-specific decoders, achieving up to 89% bandwidth savings and outperforming conventional schemes in image similarity and classification accuracy.
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.