用于自动驾驶车辆的延迟感知数字孪生辅助协作感知
Latency-Aware Digital Twin-Assisted Cooperative Perception for Autonomous Vehicles
浏览论文内容
中文总结 AI 辅助
研究自动驾驶车辆在延迟和通信资源约束下的协作感知问题，提出数字孪生辅助协作感知框架，用粗到细搜索算法解决优化问题，该算法在延迟约束下感知精度高且降低计算复杂度，框架还降低通信成本。
中文摘要 AI 辅助
本文介绍了一种数字孪生（DT）辅助的协作感知框架，旨在在端到端（E2E）延迟约束下提高感知精度，并在自动驾驶车辆的通信资源约束下平衡感知精度和E2E延迟。我们制定了一个优化问题，在延迟和通信限制下最大化感知精度，并使用新提出的粗到细搜索（CTFS）算法解决它。仿真结果表明，所提出的CTFS算法在延迟约束下实现了96.6%的感知精度，接近穷举搜索，同时将计算复杂度降低了约85.78%。DT辅助框架通过估计的、时间同步的状态更新进一步将非DT通信成本降低了50%。
英文摘要
This paper introduces a digital-twin (DT)-assisted cooperative perception framework designed to improve perception accuracy under end-to-end (E2E) latency constraints and to balance perception accuracy and E2E latency under communication resource constraints in autonomous vehicles. We formulate an optimization problem that maximizes perception accuracy subject to latency and communication limitations, and solve it using a newly proposed coarse-to-fine search (CTFS) algorithm. Simulation results show that the proposed CTFS algorithm achieves 96.6% perception accuracy, close to exhaustive search, under latency constraints while reducing computational complexity by approximately 85.78%. The DT-assisted framework further achieves a 50% reduction in the non-DT communication cost through estimated, time-synchronized state updates.
