Cooperative perception, which has a broader perception field than single-vehicle perception, has played an increasingly important role in autonomous driving to conduct 3D object detection. Through vehicle-to-vehicle (V2V) communication technology, various connected automated vehicles (CAVs) can share their sensory information (LiDAR point clouds) for cooperative perception. We employ an importance map to extract significant semantic information and propose a novel cooperative perception semantic communication scheme with intermediate fusion. Meanwhile, our proposed architecture can be extended to the challenging time-varying multipath fading channel. To alleviate the distortion caused by the time-varying multipath fading, we adopt explicit orthogonal frequency-division multiplexing (OFDM) blocks combined with channel estimation and channel equalization. Simulation results demonstrate that our proposed model outperforms the traditional separate source-channel coding over various channel models. Moreover, a robustness study indicates that only part of semantic information is key to cooperative perception. Although our proposed model has only been trained over one specific channel, it has the ability to learn robust coded representations of semantic information that remain resilient to various channel models, demonstrating its generality and robustness.

翻译：协同感知相比单车感知具有更广阔的感知范围，在自动驾驶三维目标检测中发挥着日益重要的作用。通过车辆间通信技术，各类网联自动驾驶车辆可共享其感知信息（激光雷达点云）以实现协同感知。本文利用重要性图提取关键语义信息，提出一种基于中间融合的新型协同感知语义通信方案。同时，所提架构可扩展至具有挑战性的时变多径衰落信道场景。为缓解时变多径衰落导致的失真，我们采用显式正交频分复用（OFDM）块并联合信道估计与信道均衡。仿真结果表明，在不同信道模型下，所提模型均优于传统分离式信源信道编码方案。鲁棒性研究进一步表明，仅部分语义信息对协同感知至关重要。尽管所提模型仅在特定信道下训练，但它能够学习具有鲁棒性的语义信息编码表示，该表示可适应多种信道模型，充分体现了模型的通用性与鲁棒性。