Zhixing released the urban driving assistance system and plans to carry more than 1 million passenger cars in the future

On April 19, Great Wall Motor's autonomous driving company, Navigation on HIPilot (High-speed Intelligent Pilot Assistance). It is reported that after Xiaopeng and Huawei, Zhixing is the third company to launch the urban navigation assisted driving function.

"In 2022, the competition in the autonomous driving industry will officially enter the second half, mainly focusing on the pilot intelligent driving of urban open scenes." Zhang Kai, chairman of Zhixing, said, "In 2022, the state will issue more detailed rules to regulate the ownership and safety of autonomous driving data; urban NOH will push the experience of intelligent driving to a new height; the automatic distribution of terminal logistics is on the eve of the outbreak, and the head customers will begin to deploy on a large scale of the scene." ”

"For Millais, 2022 is also a very difficult year," Zhang Kai said, how to win the "battle of data intelligence technology", "the battle of assisted driving city scenarios" and "the battle of the scale of unmanned logistics vehicles at the end" three battles, how to complete the project delivery of more than 30 models of different hardware platform models, and ensure that the delivered products meet customer expectations and have market competitiveness, is the core management of Millais in early 2022 intensive study of the topic.

Zhang Kai gave the solution idea of Zhixing in the second half of intelligent driving: effectively accumulating high-quality data; open co-creation with customers, deeply binding development; injecting user thinking into the development and iteration process of intelligent driving; reducing costs and increasing efficiency, unifying the action goals of all employees: maximizing the degree of software reuse and the efficiency of each link.

Under this idea, at this HAOMO AI DAY, Miller released the "NoH of Milliped City" equipped with HPilot3.0. From 2021 onwards, two generations of passenger car assisted driving HPilot products have been released at millimeter, and they are being delivered in an orderly manner as planned.

Gu Weihao, CEO of Miller Zhixing, said that the "Millima City NOH" can realize the main functions of automatic lane change overtaking, traffic light recognition and control, complex intersection traffic, unprotected left and right turning in the urban environment according to the driving route provided by the navigation, and can also cope with complex urban traffic scenarios such as vehicle close entry, vehicle obstruction, intersection, roundabout, tunnel, overpass.

According to reports, the "Millima City NOH" is equipped with an ultra-high computing chip with AI capability of 360T, cache 144M, and CPU computing capacity of 200K+ DMIPS; it is also equipped with 2 lidars, 12 Cameras, and 5 millimeter wave radars, which realizes the safety redundancy of the entire set of auxiliary driver perception systems to the greatest extent. Passenger car intersections equipped with "NoH of Millima City" have a pass rate of more than 70%, a lane change success rate of more than 90%, and a traffic flow processing capacity of up to 4 levels.

At present, the "NoH of the Late City" has been deeply polished in Beijing, Baoding and other cities, and the vehicle equipped with the system will also be officially mass-produced in the near future. In the future, there will be more than 100 cities where the "NoH of The Last City" function will be implemented, and the number of passenger cars will exceed 1 million units.

In order to expand the market, Zhixing is moving out of the supply model for Great Wall Motors and launching the "6P Open Cooperation Model" for the passenger car driving field, that is, the cooperation mode at the 6 product levels from the full-stack solution to the source code. As Zhang Kai introduced, Zhixing firmly creates a model with car companies, rather than a supply model.

Together with the "NoH of Miller City", there is also the product of the terminal logistics automatic delivery vehicle of Millima Zhixing - Millima Little Magic Camel 2.0.

According to the official introduction, the little magic camel 2.0 is equipped with vehicle-level hardware, ICU 3.0 large computing platform, can customize the cargo box of 600L super large cargo space; has L4 automatic driving capability, covering complex traffic scenarios such as mixed traffic and congestion, which can support the low-speed full road conditions of urban open roads, and realize contactless distribution throughout the process; in addition, it also has a number of functions such as rapid power exchange, 60~100 km cruising range, intelligent voice and touch multi-mode interaction. The terminal logistics automatic distribution vehicle factory in Baoding has been fully upgraded, covering an area of 10,000 square meters, which can achieve the production capacity target of 10,000 terminal logistics automatic distribution vehicles per year.

In December 2021, Mamo Zhixing released the data intelligence system MANA, which is the cornerstone and core source power of the evolution of all products of Mamo Zhixing.

Gu Weihao said that the perception technology of autonomous driving has undergone tremendous changes in the recent year, including the geometric growth of chip computing power, the emergence of Transformer transmodal models and the rapid improvement of Camera pixels. MANA has the latest evolutionary achievements in "perceptual intelligence", "cognitive intelligence", "cost and speed" and so on.

MANA's main technical partner is the Alibaba Cloud PAI-EFLOPS team. Through the optimization of large model training, the current model training cost is reduced by 60%, the acceleration ratio is more than 96%, and the throughput exceeds 40,000 samples per second. In addition, the automation rate of labeling AI has reached 80%, which greatly improves the labeling efficiency and reduces the cost of labeling costs. MANA has replaced traditional handwritten rules and parameters with machine learning models, completing nearly 200,000 hours of learning time, with virtual driving age equivalent to 20,000 years of human drivers.

"MANA has become the core driving force for the evolution of self-driving products." Gu Weihao said that with the maturity of automatic driving and current assisted driving technology, it can not only improve the traffic safety of the entire society, but also gradually release the driving time of drivers, alleviate driving fatigue, and improve the effectiveness of travel.

Weipai CMO Qiao Xinyu said that there is no new force in car building, only new technology. The era of smart cars is an era of hard power, and heroes are not discussed with logos. Whoever invests more in technology has the greatest chance of leading the smart track. 2022 will be the most critical year for the development of the intelligent driving industry, and the battle to win the urban scene will become the key battle to win the second half of intelligent travel.

(Editor: Zhang Shuo Proofreader: Peng Yufeng)