Semantic Communication for Cooperative Perception using HARQ

TL;DR

This paper presents a semantic communication framework for cooperative perception in autonomous driving, utilizing importance maps, OFDM, and HARQ to improve data reliability and perception accuracy over V2V channels.

Contribution

It introduces a novel semantic communication scheme with importance maps, OFDM, and HARQ, enhancing perception and throughput in vehicle-to-vehicle communication.

Findings

Outperforms traditional source-channel coding in perception accuracy.

HARQ schemes improve data reliability and throughput.

Simulation results validate the effectiveness of the proposed methods.

Abstract

Cooperative perception, offering a wider field of view than standalone perception, is becoming increasingly crucial in autonomous driving. This perception is enabled through vehicle-to-vehicle (V2V) communication, allowing connected automated vehicles (CAVs) to exchange sensor data, such as light detection and ranging (LiDAR) point clouds, thereby enhancing the collective understanding of the environment. In this paper, we leverage an importance map to distill critical semantic information, introducing a cooperative perception semantic communication framework that employs intermediate fusion. To counter the challenges posed by time-varying multipath fading, our approach incorporates the use of orthogonal frequency-division multiplexing (OFDM) along with channel estimation and equalization strategies. Furthermore, recognizing the necessity for reliable transmission, especially in the low SNR scenarios, we introduce a novel semantic error detection method that is integrated with our semantic communication framework in the spirit of hybrid automatic repeated request (HARQ). Simulation results show that our model surpasses the traditional separate source-channel coding methods in perception performance, both with and without HARQ. Additionally, in terms of throughput, our proposed HARQ schemes demonstrate superior efficiency to the conventional coding approaches.