面向网联车辆队列危险预警与远程操作的任务导向语义通信
Task-Oriented Semantic Communication for Hazard Warning and Remote Operation in Connected Vehicle Platoons
浏览论文内容
中文总结 AI 辅助
本文提出集成实例分割、单目深度估计与SD-VAE压缩的任务导向语义通信框架，通过ESM广播危险信息，实验表明其重建性能优于JPEG/JPEG2000，且7,290次模拟中碰撞率仅0.99%。
中文摘要 AI 辅助
网联自动驾驶车辆队列需要可靠地分发与任务相关的危险信息，以支持适当的下游响应，对于未解决的情况还需要远程人工干预。然而，V2X通信的有限信道带宽使得高容量传感器数据传输具有挑战性，因此促使仅交换与任务相关的信息而非原始传感器数据。本文提出了一种集成的语义和任务导向通信框架，用于自动驾驶车辆队列中的协同危险响应和远程操作。该框架将车载实例分割和单目深度估计用于任务导向的危险决策，并结合基于稳定扩散变分自编码器（SD-VAE）的语义场景压缩。与任务相关的危险信息和紧凑的语义表示通过基于广播的紧急语义消息（ESM）在现有V2X协议栈上联合分发。评估表明，SD-VAE在与任务相关的重建指标上持续优于JPEG和JPEG 2000，在低信噪比条件下表现出优雅退化而非急剧悬崖效应，证明了其在需要人工干预时用于远程场景重建的可行性。此外，一项包含7,290次模拟运行的广泛实验显示，总体车辆间碰撞率较低，为0.99%，碰撞主要发生在极端高速和短间距条件下。
英文摘要
Connected and automated vehicle platoons require reliable dissemination of task-relevant hazard information to enable appropriate downstream responses, with unresolved situations additionally requiring remote human intervention. However, the limited channel bandwidth of V2X communication makes high-volume sensor data transmission challenging, motivating the exchange of only task-relevant information rather than raw sensor data. This paper proposes an integrated semantic and task-oriented communication framework for cooperative hazard response and remote operation in automated vehicle platoons. The framework combines onboard instance segmentation and monocular depth estimation for task-oriented hazard decision-making with Stable Diffusion Variational Autoencoder (SD-VAE)-based semantic scene compression. Task-relevant hazard information and the compact semantic representation are jointly disseminated through a broadcast-based Emergency Semantic Message (ESM) over the existing V2X protocol stack. Evaluation demonstrates that SD-VAE consistently outperforms JPEG and JPEG 2000 on task-relevant reconstruction metrics, exhibiting graceful degradation rather than a sharp cliff effect under low-SINR conditions, demonstrating its feasibility for remote scene reconstruction when human intervention is required. Moreover, an extensive campaign of 7,290 simulation runs shows a low overall inter-vehicle collision rate of 0.99%, with collisions occurring mainly under extreme high-speed and short-gap conditions.
发表机构
- Islamic University of Technology（伊斯兰技术大学）
- Mälardalen University（梅拉达伦大学）
- Samsung Research America（三星美国研究院）
机构由 AI 辅助整理，请以论文原文为准。
