Successfully held | 2024 6th Intelligent Driving Mapping and Positioning Conference

On May 22, 2024, the 2024 Sixth Intelligent Driving Map and Positioning Conference, co-organized by Gasgoo and the National Key Laboratory of Surveying, Mapping and Remote Sensing Information Engineering of Wuhan University, came to a successful conclusion in Shanghai, and was held simultaneously online and offline.

With the rapid development of autonomous driving technology, high-precision maps and positioning technology have become the key driving force of smart cars. With high precision, high richness and real-time performance, high-precision maps provide crucial road information for L3 and higher-level autonomous driving systems. However, challenges such as cost, coverage and data freshness limit its large-scale application in the field of urban NOA.

In this context, the 6th Autonomous Driving Map and Positioning Conference in 2024 will focus on key technologies, development directions and the latest industry standards of maps and positioning, and will start from sub-sectors such as high-precision map data processing, GNSS modular technology, high-precision IMU, P-Box combined positioning system, SD pro map, etc., and invite many guests from different fields of production, education and research to discuss the role of maps and positioning technology in promoting the implementation of autonomous driving, and promote the innovation and development of high-precision maps and positioning technology.

This conference would like to express special thanks to 19 ecological partners including Beiyun Technology, MCT Haoli Intelligence, Meixing Technology, OxTS (Oxford Technology Solutions Co., Ltd.), Daoyuan Electronics, AAC Technologies, Kuake Intelligence, Sinan Navigation/Qintian Navigation, Jishang Navigation Technology, Beijing Lierno, and Shitu Technology for their strong support.

Brief Analysis of China's Passenger Car Market & Welcome Speech

The domestic passenger car market has gone through three stages: technology introduction, independent innovation and development, and rapid rise, and maintained rapid growth from 2001 to 2010. Since 2018, the overall domestic market has shown structural adjustment and stable growth.

Gasgoo CEO Zhou Xiaoying said that at this stage, whether automakers transform to electrification determines whether they have a future in China, while the level of intelligence determines whether consumers have a good experience. In mature markets, better quality becomes more important. The automotive industry is an industry that focuses on safety. It should provide safer and more reliable products, rather than fast-moving consumer goods, to ensure that consumers get a high-quality experience.

The current market is continuously showing new diversified phenomena, including the iteration of new technologies, innovation of business models, and the deep integration of automakers and ecosystem partners, while marketing methods are becoming increasingly rich. Automakers’ leaders are actively embracing live broadcasting and IPization, focusing on users and reshaping sales models. By switching from traditional dealer channels to APP and direct sales, customer issues can be directly fed back to the core of the enterprise, greatly accelerating the speed of response and product iteration. To adapt to this change, the supply chain and related dimensions must work closely together to jointly meet new challenges in the market.

Zhou Xiaoying | CEO of Gasgoo

Perception, Mapping and Positioning: Three Pillars and Challenges of Building Intelligent Driving

As the system platform and the brain of the autonomous vehicle, the HD map integrates vehicle network information and perception information, directly participates in vehicle control, and outputs navigation decisions. Its role in intelligent driving can be divided into different levels.

Professor Ying Shen, director of the School of Resources and Environmental Sciences at Wuhan University, mentioned that the high-precision dynamic map model consists of four layers: static data layer (road network system), real-time road information layer (congestion, events), vehicle self-test and surrounding status layer, and user model layer. This model integrates static, dynamic and user information, comprehensively covers people, vehicles and roads, and pays special attention to travel requirements such as comfort. It not only provides a basis for existing road testers, but also supports intelligent driving decisions.

In addition, the three pillars of intelligent driving are maps, positioning and signals. Among them, the vehicle-road-cloud system provides certainty through signals to make up for the uncertainty of perception. However, intelligent driving still faces random and uncontrollable "variables" such as weather changes. These challenges involve technology, ethics, morality, safety and traffic orderliness. Therefore, the development path of intelligent driving is still full of challenges and requires continuous efforts and innovation.

Ying Shen | Dean and Professor of School of Resources and Environmental Sciences, Wuhan University

Outlook on the development trend of high-precision maps for autonomous driving

From January to March 2024, the installed capacity of L2 and above intelligent driving has reached 1.94 million sets, with a penetration rate of 43%. In terms of functions, the penetration rate of the navigation assistance function (NOA) has increased significantly, exceeding 5%.

Wang Xianbin, senior director of Gasgoo Automotive Research Institute, said that among models with a price of more than RMB 200,000, the standard configuration rate of L2 autonomous driving is close to 90%, and the future growth potential is mainly concentrated in models with a price of less than RMB 200,000. Judging from the current auto show and the technical solutions of suppliers, the introduction of pure vision and cost-effective sensor solutions will accelerate the introduction of assisted driving functions in models with a price of less than RMB 200,000.

Wang Xianbin also pointed out that light maps do not mean that maps are completely unnecessary, but rather that the accuracy and reliance on maps are optimized. For smart cars, navigation maps are still necessary. The concept of light maps is to weaken the reliance on high-precision maps through other sensors or inertial navigation systems, and to enhance the perception of specific scenarios (such as traffic lights) to meet the high-level needs of smart driving.

Wang Xianbin | Senior Director of Gasgoo Automotive Research Institute

Maps help smart driving enter the second half

At present, low-level intelligent driving is close to popularization, and the competition of intelligent driving is gradually entering the second half - the competition of high-level intelligent driving. At this stage, maps, as the core support part of high-level intelligent driving, have become an important driving force for intelligent driving to enter the second half through continuous iteration and update. In 2023, with the large-scale application of urban NOA functions, many OEMs and L2++ intelligent driving domain control manufacturers put forward the slogan of "focusing on perception and light on mapping", forming a new market trend.

Zhang Yang, Chief of Autonomous Driving Perception Section of BAIC Research Institute, said that currently, the high-precision maps in mass production are mainly static maps. In the future, high-definition maps will overlay dynamic layers on static layers. The ultimate form of high-precision maps, "vehicle collaboration", uses advanced wireless communications and new generation Internet technologies to implement dynamic real-time information interaction between vehicles and roads in all directions, and conducts active vehicle safety control and road collaborative management based on the collection and integration of dynamic traffic information in all time and space, fully realizing the effective collaboration between people, vehicles and roads, ensuring traffic safety, and thus forming a safe, efficient and environmentally friendly road traffic system.

Zhang Yang | Chief of Autonomous Driving Perception Section, BAIC Research Institute

Technical Trends of High-Precision Automotive Positioning

Xiang Wei, founder and CEO of Beiyun Technology, said that high-precision positioning in the automotive field is showing three significant trends: first, the development of P-Box to P-MOUSE, realizing high-precision positioning and antenna integration; second, the global demand for intelligent driving is driving the development of positioning technology to L-BAND or PPP services, pursuing a single-chip overall solution; third, with the advancement of L3 autonomous driving research and development, functional safety has become an important consideration for high-precision positioning, meeting the L3 functional safety requirements for positioning.

The application of high-precision positioning technology for automobiles is not limited to intelligent driving, but also applies to cockpits and other fields. In the cockpit, high-precision positioning combined with LBS services and lane-level maps can significantly improve the user experience. As the cost of high-precision positioning and high-precision maps decreases, this technology is expected to become a standard feature of automobiles in the future, further improving the user's driving and navigation experience.

Xiang Wei | Founder and CEO of Beiyun Technology

Crowdsourcing accelerates the implementation of full-scenario intelligent driving

There are still many complex scenarios in intelligent driving that need to be solved urgently, such as the failure of positioning at complex intersections, the failure of lane selection before intersections, the failure of direction selection at similar intersections, etc. These problems will be further expanded as the frequency of user use increases.