Li Dongmin, CEO of Juefei Technology: Intelligent data innovation leads vehicle-road collaboration

Recently, the "Intelligent Connected Vehicle Technology Roadmap 2.0" was released. The industry reiterated the national development path of "vehicle-road-cloud collaboration" from its own technological perspective. At the same time, it should take vehicle key technologies, information interaction key technologies and basic support key technologies as the core to jointly support the development of China's intelligent connected industry.

On December 3, Juefei Technology CEO Li Dongmin attended the 2020 World Intelligent Automobile Conference and delivered a speech at the conference.

He believes that the next few years will be a stage of rapid development of "vehicle-road-cloud" collaboration. Strengthening the integration and innovation of data from all parties will release powerful technological potential for the industry and will also become the only way to build smart transportation.

Image: Li Dongmin, CEO of Juefei Technology

At the conference, Juefei Technology was also awarded "The Best Intelligent Platform" in the intelligent automobile industry in 2020. Li Dongmin said that as an "intelligent data operator" in the industry, Juefei Technology hopes to help autonomous driving and vehicle-road collaboration achieve better commercialization through data engine services.

Figure: “The Best Smart Platform” in the Smart Car Industry in 2020

Juefei Technology has the fusion computing technology for processing massive amounts of intelligent travel data. It can synchronize and integrate, classify and reorganize various data such as vehicle sensors, roads, and traffic flows in time and space, and combine cross-platform reasoning models to create a new data engine service. In response to different directions of vehicle-road-cloud construction, it can provide L2-L4 high-precision map platform, V2X fusion computing, cloud data distribution and other solutions.

As a pioneer of China's vehicle-road-cloud industry model, Juefei Technology has summarized the expansion of the "China Path" into a three-step strategy in the process of continuous technology implementation: from road digitalization to vehicle-road collaboration, and through a complete vehicle-road collaboration service industry chain, to build the ultimate goal of intelligent transportation.

Li Dongmin pointed out that the most critical issue in achieving vehicle-road collaboration is to solve the problem of data information asymmetry between vehicles and roads and other facilities, and data fusion will become more and more important in the process of vehicle-road collaboration.

In order to solve this problem, Juefei Technology proposed a vehicle-road-cloud collaboration and software-hardware integrated architecture. The goal is to promote the continuous implementation of vehicle-road collaboration in different business scenarios through a deep learning data fusion solution, a fusion computing data engine platform, and unified spatial big data.

At the same time, Juefei Technology has independently developed edge computing terminals and solutions. The solution has a powerful intelligent driving scenario data set, combined with Juefei Technology's scalable deep learning algorithm and neural network model, which integrates laser point cloud and visual data to provide accurate perception and positioning software and hardware integrated solutions for field-side vehicle-road collaboration.

Figure: Juefei Technology Edge Computing Terminal

At present, Juefei Technology has applied "edge computing terminals and solutions" to different business scenarios. In his speech, Li Dongmin showed the guests the implementation results of Juefei Technology's vehicle-road collaborative technology.

1. High-precision fusion positioning combining roadside data and RTK

In 2020, China Mobile Shanghai Research Institute and Juefei Technology jointly launched a high-precision fusion positioning solution that combines RTK and roadside assisted positioning, and applied it to scenarios such as ports, tunnels, and urban viaducts.

Juefei Technology uses roadside sensors such as laser radar and cameras, combined with laser point cloud, image and high-precision map data, to achieve real-time perception, recognition and tracking of vehicles, and output centimeter-level precision and semantic positioning results, which are transmitted to autonomous vehicles in real time through China Mobile's 5G. This approach effectively reduces the number of sensors used and the configuration standards of autonomous driving vehicles, and further improves the production ratio of autonomous driving vehicles and management.

At present, Juefei Technology is also a partner of China Mobile's autonomous driving solutions, and has become one of the first members of China Mobile's high-precision positioning ecological cooperation "Zongheng Plan".

2. Scenario-based solutions for intelligently connected urban roads

Juefei Technology's edge computing terminal solution and "lane-level traffic incident detection system" have now been implemented in the new intelligent connected demonstration zone.

The system uses data from multiple sensors such as roadside cameras, lidar, and millimeter waves, combined with edge millisecond-level real-time changes in image sequences to select target information for calculation and processing. Based on deep learning models such as image algorithms and vehicle tracking, combined with lane-level high-precision maps, the system outputs road conditions, traffic event types, and positioning information in a structured and semantic real-time manner, and transmits it to the business platform in the cloud.

This intelligent network solution realizes the digital modeling of urban traffic and builds a roadbed perception system for the park. With the help of Juefei's leading high-precision spatiotemporal data service capabilities, it realizes intelligent monitoring of vehicles, safety warnings, and collaborative operations with other vehicles in the same domain. More importantly, it provides important safety guarantees for traffic participants.

3. Road asset digitization and intelligent inspection engine

In the field of new infrastructure and smart transportation construction, Juefei Technology has launched a "road asset digitization and intelligent inspection system" in combination with edge computing terminals.

At the same time, Juefei Technology has extended the application of this system to expressways. While building a high-precision digital model of road infrastructure, it has realized automated inspection and integrated operation and maintenance management of road assets, providing effective support for intelligent management and control, intelligent maintenance and full life cycle supervision of road facilities.

This system has been implemented on key expressway sections in Anhui, Zhejiang and other places. The high-precision real-time data generated by the system will also become an important breakthrough point for the sustainable development of vehicle-road collaboration.

Looking ahead at the current stage of vehicle-road collaboration development, the wide range of areas it covers, the length of the industrial chain it involves, and the strong government support are undoubtedly sending a strong signal: the large-scale application and promotion of vehicle-road collaboration has become a potential option for China's future transportation development.

The healthy development of the "Chinese Path" of vehicle-road collaboration will require innovative business models and data openness models in the future, and especially the exploration of deep data integration in systems, management, services and other areas.

Li Dongmin said that Juefei Technology hopes to explore a broader market space for the industry through its own integration and innovation capabilities of large amounts of vehicle-side and roadside data in vehicle-road collaboration.

As a winner of Toutiao's Qingyun Plan and Baijiahao's Bai+ Plan, the 2019 Baidu Digital Author of the Year, the Baijiahao's Most Popular Author in the Technology Field, the 2019 Sogou Technology and Culture Author, and the 2021 Baijiahao Quarterly Influential Creator, he has won many awards, including the 2013 Sohu Best Industry Media Person, the 2015 China New Media Entrepreneurship Competition Beijing Third Place, the 2015 Guangmang Experience Award, the 2015 China New Media Entrepreneurship Competition Finals Third Place, and the 2018 Baidu Dynamic Annual Powerful Celebrity.