School of Electronic and Information Engineering, Beijing Jiaotong University, Beijing, 100044, China.
Institute for Integrated and Intelligent Systems, Griffith University, Brisbane , QLD, Australia.
Sci Rep. 2023 Jan 12;13(1):642. doi: 10.1038/s41598-023-27696-z.
Autonomous driving is gradually moving from single-vehicle intelligence to internet of vehicles, where traffic participants can share the traffic flow information perceived by each other. When the sensing technology is combined with the internet of vehicles, a sensor network all over the road can provide a large-scale of traffic flow data, thus providing a basis for building a traffic digital twin model. The digital twin can enable the traffic system not only to use past and present information, but also to predict traffic conditions, providing more effective optimization for autonomous driving and intelligent transportation, so as to make long-term rational planning of the overall traffic state and enhance the level of traffic intelligence. The current mainstream traffic sensors, namely radar and camera, have their own advantages, and the fusion of these two sensors can provide more accurate traffic flow data for the generation of digital twin model. In this paper, an end-to-end digital twin system implementation approach is proposed for highway scenarios. Starting from a paired radar-camera sensing system, a single-site radar-camera fusion framework is proposed, and then using the definition of a unified coordinate system, the traffic flow data between multiple sites is combined to form a dynamic real-time traffic flow digital twin model. The effectiveness of the digital twin building is verified based on the real-world traffic data.
自动驾驶正逐渐从单车智能走向车联网，参与者之间可以共享彼此感知的交通流信息。当传感技术与车联网相结合时，遍布道路的传感器网络可以提供大规模的交通流数据，从而为构建交通数字孪生模型提供基础。数字孪生不仅可以使交通系统利用过去和现在的信息，还可以预测交通状况，为自动驾驶和智能交通提供更有效的优化，从而对整体交通状态进行长期合理规划，提高交通智能化水平。目前主流的交通传感器，即雷达和摄像机，各有优势，这两种传感器的融合可以为数字孪生模型的生成提供更准确的交通流数据。本文针对高速公路场景提出了一种端到端的数字孪生系统实现方法。从配对的雷达-摄像机传感系统出发，提出了一种单点雷达-摄像机融合框架，然后利用统一坐标系的定义，将多个站点之间的交通流数据进行组合，形成动态实时交通流数字孪生模型。基于真实的交通数据验证了数字孪生的构建效果。
