Real-time Analytics
Beijing's high-level autonomous-driving demonstration zone needed a scalable way to turn road-side sensing, traffic operations, and model development into a shared operating environment instead of a collection of disconnected pilot projects.
Reported impact
Beijing E-Town created a shared infrastructure and model platform for connected-road operations and autonomous-driving development, reducing deployment cost while improving traffic performance and opening high-value real-world data to the ecosystem.
Baidu AI Cloud helped Beijing E-Town's vehicle-road-cloud operator turn the autonomous-driving demonstration zone into a data-rich operating platform. Across versions 1.0 to 3.0 of the project, Baidu participated in building standard smart intersections, cloud-control infrastructure, and a one-stop model-service environment that can ingest point-cloud, visual, and text data for autonomous-driving and traffic scenarios. The architecture links road-side sensing, data access, data mining, labeling, training, evaluation, and deployment so developers can use real traffic data instead of synthetic pilot samples. It also exposes practical operations benefits: road-side infrastructure is standardized through 'many poles in one, many sensors in one, many boxes in one' intersection design, while traffic-control models optimize queues and signal timing on live roads. In effect, the zone is both an urban operating system for connected roads and a model-development environment for autonomous-driving innovation.
Road-side devices collect point-cloud, visual, and traffic-operation data, which is ingested into the cloud-control and model-service platforms for labeling, mining, training, and evaluation. The resulting models feed both autonomous-driving development and traffic-control operations such as signal optimization, queue management, and scenario simulation across the demonstration zone.
Baidu has participated in Beijing's autonomous-driving demonstration zone from version 1.0 through 3.0 (original: 2020年10月至今，陆续参与北京高级别自动驾驶示范区1.0、2.0至3.0建设).
Standardized intelligent-roadside design reduced construction cost by more than 40% and cut average intersection delay by 30.48% (original: 路侧建设成本较最初下降40%以上…单点自适应路口车均延误率下降达30.48%).
The zone is building a traffic industry large model and one-stop model service platform across point-cloud, vision, and text data (original: 打造多模态多场景多任务的预训练交通行业大模型…建设一站式模型服务平台).
Version 2.0 completed 301 standard smart intersections and 750 kilometers of two-way road coverage (original: 完成301个智能网联标准路口建设，双向750公里城市道路实现车路云一体化功能覆盖).
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
Related
Baidu AI Cloud Sample Oct 12, 2025 Guiyang Public Security Traffic Management Bureau (贵阳市公安交通管理局) Guiyang needed a more systematic way to reduce congestion in a mountainous city where road geometry, rapid growth, and fragmented traffic-management methods made it hard to optimize signal timing and respond to changing… Average vehicle delay at target intersections fell 15%. AI Traffic Signal Control Large Model · Qianfan Application Development Platform · Qianfan Model Development Platform Baidu AI Cloud Sample Jun 19, 2025 Haikou Traffic Police Detachment After Typhoon Yagi damaged most field sensing equipment, Haikou traffic police urgently needed to restore signal-control effectiveness without waiting for every radar, camera, and detector to be rebuilt, or the city… 567 intersections were affected by the typhoon. Edge Computing Node · Qianfan AppBuilder · Qianfan ModelBuilder Baidu AI Cloud Sample Jun 19, 2025 Nanwei Software Co., Ltd. Nanwei needed a better way to help Fengning government users explore and analyze operational data because dashboards and cockpits could only display fixed views, and custom cross-team analysis cycles were too slow for… Baidu Jiuzhou Government Native Products · Qianfan AppBuilder · Qianfan ModelBuilder 