How long will it take for autonomous driving to be realized?

Recently, there was an article about a serious car accident involving a new force’s vehicle when the “intelligent driving assistance function was turned on” (please forgive me for using such a long sentence to describe this car accident, because I really don’t want to cause any trouble) (any troubles on the road) broke the Internet, making everyone once again pay attention to the technological development of autonomous driving and related social issues.

Regarding this accident, the scene process summarized from the information available on the Internet is roughly like this: Car owner A opened the car on the elevated ACC (Adaptive Cruise) and LCC (Lane Center Assist), driving in the leftmost lane at a speed of 80km/h; suddenly a vehicle stationary in the same lane appeared in front, and there was a person B behind the vehicle; owner A's The vehicle did not brake or avoid, and crashed directly into the stationary vehicle and person B, causing the death of person B behind the stationary vehicle...

According to the Internet, the owner A of the accident said: "I turned on the assisted driving system, but the system did not recognize it. I happened to be distracted at the time."

So, who should bear the responsibility for the accident? The owner of the car that caused the accident? Or the designer and manufacturer of the car?

Although I have never purchased any vehicle with such "advanced" intelligent driving functions, I don't know how the vehicle user manual or user agreement is written, but according to the current regulations of various car companies It is a common practice that when a vehicle performs intelligent driving functions, the owner must be responsible for monitoring road conditions at all times and must be ready to take over the vehicle at all times.

Because, no matter how loudly everyone trumpets it in advertisements, everyone knows very well that current smart driving cannot be called autonomous driving at all, it is still just assisted driving. It can only provide the driver with assistance functions while driving and cannot achieve the purpose of replacing the driver.

According to Article 51 of the "Shenzhen Special Economic Zone Intelligent Connected Vehicle Management Regulations", if a driver's intelligent connected vehicle encounters a road traffic safety violation, the public security organ shall The management department will deal with the driver in accordance with the law. Article 54 stipulates that if a traffic accident involving an intelligent connected vehicle causes damage due to defects in the vehicle itself, the driver or owner or manager of the vehicle may request compensation from the manufacturer or seller in accordance with the law after completing the prescribed compensation.

It can be seen from the above regulations that in the event of an accident, the driver is still the first responsible person. If it can be proven that the vehicle itself is defective, he can request compensation from the car company . But, how can an ordinary consumer prove that the vehicle is defective?

We do not want to analyze the cause of this accident in detail-it is the design of the vehicle itself. Defects are still the driver's responsibility; I just want to analyze the current status of intelligent driving starting from this accident.

According to the SAE J3016 autonomous driving classification standard, at levels below L3, although operations such as steering, acceleration, and deceleration can be handled by the vehicle’s automatic autonomous driving system, the human driver is still responsible. Monitor all conditions on the road surface. In other words, at levels below L3, the autonomous driving system is only an assist, and the driver has full responsibility for the safe operation of the vehicle.

According to this division of responsibilities, when the current autonomous driving technology is far from mature, various L2.5, L2.9, L2.9, etc. A rather "creative" naming method with Chinese characteristics.

Every OEM is playing around with things, and no one dares to say that their autonomous driving system can reach L3. Because once it is declared to be L3, the responsibility for accidents when the vehicle is in L3 autonomous driving state needs to be borne by the car company.

In this state, on the one hand, everyone has to compete with each other in terms of technical strength and continuously introduce more advanced autonomous driving functions in the hope of selling more cars; on the other hand, I dare not cross the border of L3 even half a step. Because, as long as it is not L3, then all accidents have nothing to do with you. At least it is clearly stated in the user's manual that the driver has the responsibility to be ready to take over the vehicle at any time.

However, in fact, let us think about this from another angle. When you participate in a meeting that does not require you to speak or record content, will you doze off, look at your mobile phone, In a daze... The current assisted driving function of L2. The system will alarm and remind you to monitor the road attentively.

This situation is as if you have found a full-time driver, and then you have to supervise him at all times while he is driving. When a dangerous situation occurs, if the professional driver fails to take action, you must intervene in time, otherwise you will be responsible for the accident.

Do you think this situation is a bit anti-human? Do people who buy cars with self-driving functions like to be driving school instructors? If self-driving functions require our full attention, and it is difficult for us to maintain our full attention all the time, are these functions still so meaningful?

I am not someone who is against autonomous driving technology. On the contrary, I strongly support the development of autonomous driving technology. I believe that when autonomous driving technology matures in the future, everyone will be able to save a lot of time and energy, and the number of traffic accidents will be greatly reduced. However, current autonomous driving is far from mature enough to be popularized on a large scale. Not only is it far away from high-level autonomous driving, but even basic auxiliary functions such as AEB, LKA and parking cannot be 100% reliable.

## (Image source: SAE International)

In 1918, Scientific American magazine published an article titled “A Motorist’s Dream: A Car Controlled by a Set of Keys "Car" image (pictured below), showing a self-driving tram. The article believes that "...in the future, cars with steering wheels will be as obsolete as today's cars with hand pumps!"

(Picture source: Scientific American)

In the past nearly a hundred years, humans have been interested in autonomous driving. With persistent pursuits and unrealistic fantasies, I always feel that autonomous driving will be achievable in 20 years. Unfortunately, until today, no one can accurately say when a car that completely eliminates the steering wheel will be able to drive on the road. And as people get closer to this dream, they are increasingly aware of the difficulty and complexity of achieving fully autonomous driving.

The realization of autonomous driving does not rely on the vehicle itself, but on the efforts of the entire transportation system. It is not just relying on OEM and autonomous driving suppliers, but relying on the common progress of all fields of society.

The following are some inspired suggestions:

1. Improve the standards for the accident data recording system of the intelligent driving system.

Although the country already has relevant standards for EDR (Event Data Recorder, automobile event data recording system), it can only record basic information about the vehicle. At this stage, whether intelligent driving fails or not is still decided by the car companies, and there is no effective third-party supervision. Because, with the massive amount of complex data, no one except the car companies and their suppliers can tell exactly what happened. The fundamental reason for this phenomenon is that there is no more detailed national standard with relevant content. What is the meaning behind each data, which data must be stored at what time, etc. These requirements are still lacking. It is recommended that relevant institutions and associations can refer to the practice of automobile OBD to establish corresponding standards as soon as possible and continuously improve them.

#2. The country should establish a unified driving scene simulation database and simultaneously inject detailed information on traffic accidents.

The improvement of autonomous driving algorithms requires the accumulation of massive data. It is difficult for any single company to complete this level of data accumulation in a short period of time on its own. Only by changing the situation of each enterprise working alone, forming a win-win situation of co-creation, and learning from the practice of open source software, can we gather the strength of the whole country to make our intelligent driving truly at the forefront of the world.

#3. For vehicle access, regulatory authorities should issue more detailed testing and certification standards as soon as possible.

Although intelligent driving is still in the development stage and system solutions vary widely, some basic principles and methods can still be defined at this stage. Moreover, once a nationwide driving scene simulation database is established, it can be used as a benchmark to test all newly admitted vehicles in the cloud. Avoid lengthy road tests and reduce costs.

#4. Find a way to manage OTA that is both efficient and reliable. Due to the rapid iteration of autonomous driving algorithms, car companies must continuously update software through OTA. The current supervision of OTA adopts a filing system, which leads to the possibility that the functions and performance of vehicles that were originally admitted may undergo major changes after OTA. How to find an efficient and reliable OTA management method is a major challenge facing the current automotive industry supervision.

Finally, I would like to express my sincere blessings to those companies that have invested their money in autonomous driving. I hope you all have enough resources and patience to survive the long night and see the light of dawn!

The above is the detailed content of How long will it take for autonomous driving to be realized?. For more information, please follow other related articles on the PHP Chinese website!