□ Dahe Daily Yu video reporter Xie Yuanli
On April 25, the 2024 Beijing Auto Show was grandly opened. As a leading enterprise in the mass production of autonomous driving in China, Yihang Intelligent officially released the "Duxing" urban intelligent driving platform, using the mass-produced BEV "Lingmu", including the urban intelligent driving standard version, the urban intelligent driving performance version and the urban intelligent driving all-round version of three series of solutions, among which the first urban intelligent driving standard version based on the horizon journey 6E covers high-end intelligent driving functions such as extreme performance high-speed NOA and urban memory pilot, and the price of the whole set is not higher than 5000 yuan, which will provide users with a cost-effective urban scene intelligent driving solution.
Since taking the lead in mass production of the NOA integrated driving and parking solution in 2022, Yihang Intelligent has continued to make efforts to lead the field of assisted driving NOA by relying on full-stack self-developed technology and rich mass production experience, and accelerated towards a new scenario of urban intelligent driving. At the press conference, Yihang Intelligent announced that it has reached a strategic cooperation with Horizon, an industry-leading provider of high-performance intelligent driving computing solutions, and officially joined the first batch of software algorithm partners of Journey 6, and the two sides will work together to promote the mass production of high-end intelligent driving to a new stage.
Leading the way to the evolution of NOA mass production of assisted driving
As one of the earliest autonomous driving technology companies in China, Yihang Intelligent has always adhered to the goal of mass production, and has determined a gradual development path since its establishment in 2015. With the evolution of technology, Yihang Intelligence has not only accumulated a lot of experience in mass production of autonomous driving technology, but also clarified a complete mass production route for autonomous driving.
The NOA function is an important node on the mass production route of autonomous driving. Before the advent of NOA, all assisted driving functions were fragmented, but NOA implements point-to-point autonomous driving functions, thus bringing users an immersive driving experience. The development route of autonomous driving is based on the path of NOA's mass production plan.
In 2022, based on high-precision maps and visual convolutional neural network technology, Yihang Intelligent took the lead in mass production of high-speed NOA, which is also widely regarded by the industry as the first year of mass production of high-speed NOA. On the basis of high-speed NOA technology, the NOA function has two major development directions, one is to expand high-speed NOA scenarios, and the other is to improve the product performance of existing high-speed NOA. Starting from these two directions, in 2024, Yihang Intelligent will successively add urban application scenarios on the basis of high-speed NOA, develop the urban memory navigation function, and introduce BEV algorithms for high-speed NOA to improve the perception performance of high-speed NOA. In the next stage, with the data accumulation and algorithm iteration of the NOA function in urban scenarios, it is expected that urban NOA will be realized with BEV perception + no map technology solution within one to two years, and lay the foundation for end-to-end autonomous driving in the future.
Focusing on the present, by adding a road memory module on the basis of the high-speed NOA algorithm framework, Yihang Intelligent has realized the urban memory navigation function. Among them, more than 85% of the new functional algorithms are derived from the reuse and fine-tuning of high-speed NOA algorithms, that is, the mass production of high-speed NOA algorithms is equivalent to having the backbone algorithms of urban intelligent driving.
At the same time, through the iteration of the high-speed NOA algorithm, the performance of high-speed NOA can be improved in the dimensions of traffic efficiency, perception ability, and safety, so that high-speed NOA can truly be used from usable to easy to use. For example, by optimizing the multi-lane path planning and traffic flow monitoring mechanism, the efficiency of automatic overtaking and merging is improved, so as to achieve higher traffic efficiency, and by improving the detection range of road boundaries, the temporary road construction scene can be identified more accurately, and the technical scheme of emphasizing perception and ignoring map can be realized.
From the perspective of mass production, Yihang Intelligent has demonstrated its core strength in the competition of autonomous driving technology by leading the evolution of NOA in assisted driving.
Production-grade BEV Osmo: Expanding the boundaries of urban intelligent driving
In the mass production evolution of the pilot assisted driving NOA, the mass-produced BEV "Lingmu" developed by Yihang Intelligent Full-stack is an important part of the "Duxing" platform, shouldering the important task of expanding the boundaries of urban intelligent driving.
Whether it is high-speed NOA or urban memory pilot, it is a point-to-point autonomous driving realized in a specific scenario, and it cannot cover the entire city. In order to further expand the urban intelligent driving scenario, it is necessary to introduce BEV perception algorithms, and in order to promote BEVs to meet the conditions for mass production at the vehicle specification level, it is necessary to combine the core modules of traditional perception algorithms as a supplement to realize the necessary capabilities such as telefocus perception and traffic sign recognition. In addition, the mass production of traditional perception algorithms is also an important definition of the mass production conditions of BEVs, and only after mass production of traditional perception algorithms can the BEV meet the mass production conditions.
Yihang Intelligence is one of the few autonomous driving companies in China that has developed its own perception algorithm to mass production, and the traditional multi-camera fusion perception solution can realize rapid identification under occlusion and accurately distinguish high-density targets at far/medium/short range. The production-grade BEV "Osman", which is the same as its perception solution, also absorbs these excellent capabilities. At present, the "Osmo" has been successfully transplanted to the Journey 6E platform, matching high-end intelligent driving functions such as high-speed NOA with extreme performance and urban memory navigation, and will be further expanded and upgraded in the future to achieve full-scene autonomous driving. It is worth mentioning that the Horizon Journey 6E solution can also provide a variety of configurations according to customer needs, taking into account both cost and functional needs.
In the face of the ultimate goal of unmanned driving, Yihang Intelligent starts from full-stack self-development, takes technology as the foundation, accelerates the mass production and evolution of NOA around core scenarios, breaks through the commanding heights of the intelligent driving industry, and is committed to becoming a global AI intelligent driving solution provider.