标签： 上海中低端龙凤

Since the launch of the end-to-end intelligent driving system "FSD V12 beta" in the United States in August 2023, end-to-end has become the hottest topic in the automobile industry. With the follow-up of Huawei, Tucki, Weilai, Ideality and other enterprises, almost every domestic manufacturer will spend a lot of space in the press conference to publicize how powerful their end-to-end is. Regardless of marketing methods, what does "end-to-end" mean? What does it mean for intelligent driving? Today we will explain this question to you!

Before the end-to-end intelligent driving system was mass-produced, every intelligent driving system adopted a modular scheme. Simply put, modular intelligent driving is an assembly line, which mainly includes four processes: perception, prediction, planning and control. First of all, the task of the sensing part is to process the data of sensors such as radar and camera of the vehicle, and then analyze the specific position and road trajectory of the objects around the vehicle, and distinguish whether they are pedestrians, bicycles, cars or trucks.

Then, the perception module will transmit the above information to the prediction module, and the prediction module will analyze the next movement state of the surrounding traffic participants according to the above information, such as whether the surrounding vehicles will turn, go straight or stop next. After further analysis, the prediction module will provide one or more driving paths and vehicle speeds that the vehicle can refer to next.

Then the prediction module sends the road driving scheme of the vehicle to the planning module, and the planning module will decide what the vehicle should do next according to the information such as the vehicle’s own state and navigation. After the planning module confirms the driving path and speed, it will transmit the command to the control module, and then the control module will calculate and operate the steering wheel, brake and throttle of the vehicle. A seemingly simple intelligent driving function is realized through the above steps.

From the above introduction, it is not difficult to see that modular intelligent driving decomposes simple driving behavior into multiple steps, and the logic of each step is in perfect harmony. In the eyes of car companies and suppliers, modular intelligent driving itself is a very good solution, because different teams can be responsible for the corresponding modules and give full play to the advantages of division of labor and cooperation, thus rapidly changing intelligent driving from concept to mass production.

Secondly, modular intelligent driving has a set of system framework with clear functions and responsibilities, so when the intelligent driving system finds bugs in use, car companies and suppliers can immediately find the specific reasons for the bugs and quickly fix them through OTA. For example, if the vehicle brakes wrongly when driving at high speed, then through data analysis, the vehicle enterprise can know whether the fault is due to the wrong data of the sensing module or the wrong judgment given by the forecasting and planning module.

Although modular intelligent driving is convenient for mass production and BUG repair, it needs to learn a lot of traffic rules and driving experience if it wants to control vehicles like people, and all this depends on engineers to define the rules in advance, that is, to turn traffic rules and driving experience into lines of software code. But can engineers write code to cover all the driving scenes in reality? Of course it’s impossible! On this issue, there is a classic case in the industry. If you drive a vehicle on a narrow road full of cars on both sides, a balloon suddenly floats on one side of the road, then the general logic will think that there may be children jumping out on one side of the road, so the vehicle should brake immediately. However, the same scene is placed on the high speed. If the intelligent driving system still controls the vehicle by braking immediately, it is likely to turn into a rear-end collision. In other words, if engineers don’t define the rules in advance for this kind of driving scene, such as the system doesn’t brake after the balloon is detected at high speed, then the intelligent driving system will have safety risks when it encounters similar scenes.

According to Xpeng Motors, a relatively stable mass production intelligent driving system has about 100,000 rules. And if the intelligent driving system is to be close to the same level as people, it needs to manually write about 1 billion rules. For software engineering development, this is almost impossible. Because of this, we can see that the traditional intelligent driving system will make more or less mistakes in daily use, so that drivers have to intervene.

For the above reasons, car companies that focus on autonomous driving have been trying to solve the problem that traditional intelligent driving needs preset rules, so there is an end-to-end approach. The so-called end-to-end, in fact, is to make all the traditional sub-modules of perception-prediction-planning-control neural network, that is, to replace the traditional algorithms and manually written rules with advanced algorithm models.

Therefore, the end-to-end workflow is quite different from the traditional modular workflow. The traditional modular work sequence is perception-prediction-planning-control in turn, while the end-to-end sequence is sensor data (radar, camera)-neural network-driving parameters (steering wheel, throttle, brake), that is to say, the traditional perception, prediction, planning and control modules are all completed by neural network.

As can be seen from the workflow, the core technology in end-to-end is neural network, and the technology most closely related to neural network is AI. In the past two years, AI has shown great performance in the fields of voice, text, pictures and video, and everyone should have realized it. When the neural network is applied to the car, it means that people can constantly train the intelligent driving system, so that it can learn to adapt to more complex driving environment.

Therefore, at the functional level, the biggest change from end to end is that the system has the ability of autonomous learning, which is a function that traditional modular intelligent driving does not have.In this way, when dealing with all kinds of unexpected real driving scenes, end-to-end can calculate the appropriate rules through neural network, without having to manually write the rules in advance, which also provides a solution for intelligent driving to deal with endless driving scenes in reality.For example, the Tesla FSD V11 version, which didn’t have end-to-end function before, has written more than 300,000 lines of code, while the end-to-end FSD V12 version has directly reduced more than 300,000 lines of code to 2,000 lines, but the performance of FSD V12 is closer to human drivers than V11.

fromIn theory, end-to-end is indeed a very ideal technology, but in practice, end-to-end is not so reliable. This is because people’s understanding of neural networks is still not clear enough at this stage, so people also call neural networks "black boxes". As shown in the above figure, in the white box state, we are very aware of the logical causal relationship between system input/output, but when the input information passes through the black box, people can’t explain why the input information becomes the output information.

For example, when there is an obvious logical error in the intelligent driving system, the vehicle manufacturer can quickly find out which module the problem is, and then manually write a new rule. But in the end-to-end system, car companies do not know which parameter or structure in the complex neural network has problems.

For this reason, the end-to-end intelligent driving system based on neural network can sometimes give reasonable rules in very complicated scenes, but sometimes it will make very low-level mistakes, such as not being able to distinguish traffic lights, so some people describe it as "the upper limit is very high and the lower limit is very low". Considering that there are some risks in the end-to-end application, the end-to-end intelligent driving system introduced by Huawei and Tucki does not rely entirely on autonomous learning, and their end-to-end systems still have many manually written rules to cover the intelligent driving system.

From the perspective of technology development trend, end-to-end is definitely the direction of high-level intelligent driving in the future. However, because people’s understanding of neural networks is not thorough enough, the end-to-end performance of various companies at this stage still has a certain gap with the ideal level. In addition, compared with the existing modular intelligent driving system, whether the end-to-end neural network algorithm model is smart or not depends heavily on massive real data for training. Only after massive data training, the neural network can be transformed from a small model to a usable large model, which means that high-order intelligent driving requires huge computing power and data input in the development stage, thus invisibly raising the threshold of intelligent driving. Because of this, some car owners will feedback that their cars are not as good as they used to be after upgrading to end-to-end intelligent driving. This is the painful period of big model training. Considering that there are great differences in end-to-end training among different brands in reality, this means that the performance gap of different brands of intelligent driving systems may be gradually widened in the future.

Cctv newsAccording to the website of the National Bureau of Statistics, according to a survey of 69,000 cultural and related industrial enterprises above designated size (hereinafter referred to as "cultural enterprises"), in 2022, cultural enterprises realized an operating income of 12,180.5 billion yuan, an increase of 0.9% over the previous year.

　　In terms of formats, the operating income of 16 industry subcategories with obvious characteristics of new cultural formats reached 4,386 billion yuan, up 5.3% over the previous year and 4.4 percentage points faster than that of all cultural enterprises above designated size.

　　By industry category, the operating income of news information service was 1,446.4 billion yuan, up by 3.3% over the previous year. Content creation and production reached 2,616.8 billion yuan, an increase of 3.4%; Creative design service was 1,948.6 billion yuan, down by 0.2%; Cultural communication channels were 1,312.8 billion yuan, down by 1.0%; Cultural investment operation was 50.4 billion yuan, an increase of 3.2%; Cultural entertainment and leisure services reached 114.1 billion yuan, down by 14.7%; Cultural auxiliary production and intermediary services were 1,651.6 billion yuan, down by 0.6%; The production of cultural equipment was 690.4 billion yuan, up by 2.1%; The output of cultural consumption terminals was 2,349.4 billion yuan, an increase of 0.3%.

　　In terms of industrial types, the operating income of cultural manufacturing industry was 4,478.1 billion yuan, an increase of 1.2% over the previous year; Cultural wholesale and retail trade was 1,937.6 billion yuan, down by 1.2%; The cultural service industry was 5,764.8 billion yuan, an increase of 1.4%.

　　In terms of fields, the operating income of cultural core areas [3] was 7,489.1 billion yuan, an increase of 1.3% over the previous year; Cultural-related fields reached 4,691.4 billion yuan, an increase of 0.2%.

　　In terms of regions, the eastern region realized an operating income of 9,171.4 billion yuan, an increase of 0.1% over the previous year; The central region was 1,826.9 billion yuan, an increase of 5.8%; 1,079.3 billion yuan in the western region, an increase of 0.5%; Northeast China was 102.9 billion yuan, down by 1.0%.

　　Xinhuanet Beijing, August 28th (Wang Kunshuo, Zhang Xinxin) Every autumn and winter, the flu will "arrive as scheduled", but its severity is still underestimated. At the 2019 academic exchange meeting on seasonal influenza prevention and control strategies sponsored by the Chinese Preventive Medicine Association and supported by Sanofi Pasteur, experts attending the meeting reminded that influenza vaccination is the most effective means to prevent influenza, which can significantly reduce the risk of influenza and serious complications among vaccinators.

　　Influenza is not a common cold, and its harm is underestimated.

　　As an acute respiratory infectious disease, influenza is not a common cold. Influenza virus directly attacks human respiratory system, which can cause many serious life-threatening complications such as viral pneumonia, secondary bacterial pneumonia, acute respiratory distress syndrome, shock, disseminated intravascular coagulation and so on.

　　Influenza virus is changeable, and it will appear in a brand-new appearance every winter, causing seasonal epidemic. Influenza and its complications have always been seriously underestimated by the whole society. The World Health Organization (WHO) estimates that the seasonal epidemic of influenza can cause 290,000 to 650,000 deaths worldwide every year.

　　Feng Luzhao, Director of Respiratory Infectious Diseases Department, Infectious Diseases Department, China Center for Disease Control and Prevention.

　　Feng Luzhao, director of the Respiratory Infectious Diseases Department of the Infectious Diseases Department of China Center for Disease Control and Prevention, said that the disease burden of influenza is very serious, and the incidence of influenza in the whole population can reach 5%-10% every year, and children can reach about 20%.

　　It is understood that the high-risk population of influenza is divided into two categories: one is the population with high risk of serious complications of influenza, including the elderly over 60 years old, children aged from school age to 5 years old in June, pregnant women and patients with chronic diseases; The second category is people with high exposure risk, including school students and medical workers.

　　Feng Luzhao said that the current statistics of the number of cases and deaths can not fully reflect the true level of influenza, and the number of influenza patients diagnosed is less than the actual number of cases. At the same time, it also involves the attribution of death caused by influenza.

　　"The flu will cause serious complications such as pneumonia, and it will also aggravate other chronic diseases of patients themselves. These patients who died will not be classified as flu deaths, but will be blamed for their complications, such as pneumonia, chronic obstructive pulmonary disease, diabetes complications, etc." Feng Luzhao said.

　　Strengthening vaccination awareness and improving vaccine value cognition

　　At present, vaccination is the most economical and effective intervention measure for influenza prevention and control, and vaccination for high-risk groups is recommended first.

　　Dr. Lance E. Rodewald, Senior Advisor, Immunization Program, China Center for Disease Control and Prevention.

　　It is reported that since 2007, Beijing has carried out a large-scale free vaccination campaign among local registered elderly and primary and secondary school students over 60 years old in order to effectively control and prevent influenza and protect public health.

　　For patients with chronic diseases, Dr. Rodewald, senior consultant of immunization program of China Center for Disease Control and Prevention, thinks that many pilot studies including China can be used for reference: for example, if influenza vaccination is included in the nursing standards of patients with chronic diseases such as asthma, chronic obstructive pulmonary disease, diabetes, etc., doctors should first realize the importance of influenza vaccination in avoiding the aggravation of the disease.

　　Du Xin, director of the Department of Cardiology, anzhen hospital, Capital Medical University.

　　In this regard, Du Xin, director of the Department of Cardiology, anzhen hospital, Capital Medical University, said that influenza vaccine can prevent myocardial infarction. She cited the evidence mentioned in the paper published in the New England Journal of Medicine: influenza is clearly related to myocardial infarction, which will increase the risk of myocardial infarction by six times.

　　"We have done a wide range of statistics, 33% of the hospitalized patients with heart failure in China were induced by infection, including the flu. If you want to control the infection from the source, controlling the flu is also a very important factor. " Du Xin said.

　　However, the importance of influenza vaccine has not been fully recognized by the whole society. At present, the total coverage of influenza vaccine in China is less than 2%.

　　Du Xin said that there are even a small number of grassroots doctors and community doctors who think that people suffering from cardiovascular diseases cannot be vaccinated with influenza vaccine. Medical staff need to raise their awareness of the value of vaccines and help patients reduce their misunderstanding of influenza vaccines.

　　"In the future, I think that doctors should recommend influenza vaccination in the doctor’s advice to high-risk patients including cardiovascular diseases, which will be of great help to improve the vaccination rate and reduce the acute attacks of some patients with chronic diseases." Du Xin said.

　　"I hope that China can speed up the introduction of more products and better help key populations improve vaccine protection." Feng Luzhao believes that the support at the national level is of great significance to improving the vaccination rate. In order to strengthen people’s understanding of the necessity of influenza vaccination, it is necessary to vigorously carry out health education, encourage the strengthening of investment in public vaccines, promote the policy of benefiting the people, and further build a more convenient and accessible vaccination service system.

　　Medical staff are high-risk groups of influenza, so we should strengthen protection.

　　Medical staff themselves are highly exposed to influenza, but their awareness of influenza prevention and control needs to be improved. Du Xin learned from personal experience that the influenza vaccination rate of medical staff is relatively low.

　　"Many medical staff, like the general public, are also lucky enough to think that influenza vaccine is a preventive measure, and it is just as well not to vaccinate. But in fact, medical staff will encounter many patients during the consultation. They are always in a state of high exposure to the virus, and the risk of infection in the flu season is 3-4 times higher than that of the general population. "

　　Du Xin believes that doctors and nurses, especially those working in emergency departments and departments related to respiratory diseases, belong to high-risk groups of influenza. "How to make our medical staff and the whole society realize the preventive value of influenza vaccine is a task that we need to work hard together and the government needs to continue to strengthen guidance."

　　The public still has misunderstandings about influenza vaccine.

　　At present, the public still has misunderstandings about influenza vaccine, such as ineffective vaccination effect and inability to prevent influenza. In this regard, Feng Luzhao said that influenza vaccine is recommended according to the strains predicted by WHO every year and needs to be vaccinated every year. In this case, first of all, it is not excluded that the recommended strains are not completely matched with the actual epidemic viruses, so the vaccination effect of influenza vaccine will be different every year.

　　"This is limited by the current technology, and it cannot be accurately predicted. The universal flu vaccine has not yet been developed. However, if the matching rate is good, the protective effect of the vaccine can reach 70-80%. If the matching is not good, the protective force can only reach 20-30%. " Feng Luzhao said.

　　In addition, the effect of the vaccine is related to the vaccination rate. Feng Luzhao said that if the vaccine has a moderate protective effect of 50%, as long as the vaccination rate is high enough, it can still form an immune barrier, reduce the incidence rate and reduce the medical expenses of individuals and countries.

　　Secondly, many respiratory viruses and bacteria, such as respiratory syncytial virus, adenovirus, or streptococcus pneumoniae infection, can cause symptoms similar to influenza. Influenza vaccination can prevent influenza virus infection, but it can’t prevent respiratory tract infection or common cold caused by other viruses. In fact, many people still have cold symptoms after being vaccinated with influenza vaccine, but it is not the flu.

　　Influenza vaccine is not recommended in priority. It should be vaccinated before the flu season.

　　The flu season is high in autumn and winter, and it reaches its peak in January. Talking about the best time for vaccination, Feng Luzhao believes that people had better get the flu vaccine before the epidemic season comes. During this period, it will take several weeks to produce antibodies after vaccination to ensure the protection of human body before the peak period of infection risk comes; Even if the vaccination is not completed before the arrival of the flu, as long as there is no flu infection, people can be vaccinated throughout the epidemic season. "Early vaccination is better than late vaccination, and late vaccination is better than no vaccination." Feng Luzhao said.

　　In addition, in view of the fact that babies under 6 months old can’t be vaccinated with influenza vaccine, family members and caregivers of children are recommended to be vaccinated, so as to provide a safe and secure nursing environment for children, and pregnant women are encouraged to be vaccinated with influenza vaccine to prevent influenza attack.

　　Feng Luzhao said that according to the "Technical Guide for Influenza Vaccination in China (2018-2019)", people who can be vaccinated with different types of vaccine products from different manufacturers can voluntarily vaccinate any kind of influenza vaccine, and there is no priority recommendation. At present, influenza vaccine has been listed, and residents can make an appointment and vaccinate at the inoculation point of the community health service center in their jurisdiction.

In order to pursue a more relaxed and pleasant travel experience, we are eager to have a car that is not only comfortable but also full of intelligent technology. The Lectra 08 EM-P, an outstanding masterpiece of this Lectra brand, undoubtedly satisfies all our imaginations of the ideal car. In many aspects, such as original design, intelligent cockpit, luxury comfort and intelligent driving, it has brought unprecedented driving enjoyment to family users who pursue individuality and quality.

The design of Lectra 08 EM-P is inspired by The Next Day concept car, and its design language is unique and futuristic. The body lines are smooth, the urban skyline technology belt and the unbounded vehicle side design complement each other, and the Yingneng crystal penetrating taillights are the finishing touch, and every detail skillfully combines technology and aesthetics.

This model is equipped with the Flyme Auto intelligent cockpit system deeply integrated with Meizu. With the powerful performance of two domestic self-developed 7nm "Longying No.1" chips, it brings users an extremely smooth operating experience. The 15.4-inch ultra-clear full screen is perfectly combined with the 12.3-inch full LCD instrument, and all driving information is clear at a glance.

Lectra 08 EM-P is not only a car, but also a "third space" for the whole family. Its super quiet cockpit design, combined with streamer ambient lights and shallow Nappa advanced leather seats, creates an extremely luxurious riding environment. Moreover, its front and rear four seats are equipped with ventilation, massage and heating functions, which is a unique configuration in the same class SUV, so that the whole family can enjoy the ultimate comfort and comfort when traveling.

In terms of intelligent driving, the Lectra 08 EM-P also performed well. It is equipped with the intelligent driving computing platform of Yikatong Tianqiong Pro, and is equipped with up to 28 high-perception hardware, providing excellent NOA pilot driving assistance functions. Whether it’s smart going up and down the ramp, smart driving into the fast lane or smart shifting the lever to change lanes, it can easily cope with it, making driving easier and safer.

Looking back on the sales success of the National Day Golden Week, the "Super Gemini"-Linke 08 and Linke 07 jointly set a brilliant record of selling 8,000 units in 7 days. This achievement not only shows the strong strength of the brand, but also proves the excellent product strength of LECK 08 EM-P.

With its original design with high recognition, luxurious intelligent configuration of Yueji Yuejia, high-end electric hybrid EM-P system with energy saving and excellent performance, and global safety and reliability, Linke 08 EM-P successfully broke through the homogenization competition barrier in the home SUV market and became a new benchmark in the high-end electric hybrid SUV market. Choosing LECK 08 EM-P means choosing a smarter, more luxurious and safer way to travel, making every driving a wonderful journey.

Nowadays, most consumers attach great importance to security configuration, which can be dispensed with but cannot be dispensed with. A more comprehensive configuration can often win more consumers’ love. What I bring to you today is a-. Now let’s follow Xiaobian to see what it has done.

Let’s look at the appearance of the tank 300 first. The front face of the tank 300 looks hard and very recognizable. Coupled with the concise headlights, the visual effect looks quite sharp. The car is equipped with LED daytime running lights, front fog lights, automatic opening and closing, adaptive far and near light, delayed closing and so on. Coming to the side of the car, the body size of the car is 4760MM*1930MM*1903MM. The car adopts fashionable lines, which gives people a very elegant feeling. With large-sized thick-walled tires, it looks full of sports. Looking back, the overall shape of the rear of the car echoes the front face, and the taillights look very fashionable. Coupled with the unique exhaust pipe, it is still relatively domineering overall.

When I came to the tank 300, the interior looked very individual and very solid. The steering wheel of the car is very in line with the interior style, made of leather and full of design. From the central control point of view, the central control screen with 12.3-inch touch-sensitive LCD makes the interior design layered and looks young. The dashboard and seats give people a good feeling, too. Let’s take a look. The car is equipped with a young dashboard, and the information can be read easily and clearly. The car uses leather seats, the seats are wrapped in place, the materials are exquisite and the ride is comfortable.

The car is equipped with car networking, driving mode selection, remote control key, Bluetooth key, rear wiper, interior atmosphere light and other configurations, and the configuration performance is passable and basically satisfactory.

The SUV has an atmospheric appearance, good spatial performance and high cost performance. I wonder if you are interested in it. If you go offline and actually experience it, it is estimated that there will be many new gains.