Rewrite the Technological Landscape

After Musk left, Meng Qian directly made appointments with BYD's Wang Chuanfu and Geely's Li Shufu, because many things are not waiting for people, and these two companies have been moving frequently recently.

"I heard that both BYD and Geely have begun to increase investment in electric vehicles."

"This year, Omi vigorously promoted electric vehicles. After the Copenhagen conference, electric vehicles have become a hot topic in the industry. Meng always knows it. I have always believed in the future of electric vehicles." Probably because of Li Shufu's presence, Wang Chuanfu's words are obvious. keep it.

In fact, the two knew that they were a little surprised when they were being appointed at the same time. At this moment, the two companies are gradually becoming equal. They are rivals anyway, even if Dafeng Group is a major shareholder, but Meng Qian said today is here to talk about future plans and competitors. Sitting together and chatting about future plans, it feels wrong no matter what.

Sure enough, Li Shufu was just a very official polite sentence, "We still have a lot to learn from BYD in the development of electric vehicles."

Knowing the two people’s careful thinking, Meng Qian went straight to the subject, “I’m looking for two of you today and want to tell them that I am ready to reconcile with Musk.

Meng Qian probably talked about the matter.

"Tesla's research and development results on the motor system this year are indeed very valuable." Li Shufu is still more convinced about Tesla's technology. After all, Geely did not develop this direction when Tesla was fully engaged in pure electric vehicles. .

But Wang Chuanfu is obviously not reconciled. “In fact, we have a lot of patent overlaps with Tesla, and we are also accelerating patent applications recently.”

"In fact, it is precisely because of BYD's development that I want to get Tesla's patents over, so that when the two sides are combined, we have the opportunity to impact more advanced technologies."

The two nodded and agreed with Meng Qian’s statement, and then waited for Meng Qian to continue. After all, they didn’t know what Meng Qian wanted to talk about when he came to him. As a result, Meng Qian directly changed the subject. The two will say hello first, and the specific situation will be discussed after I reach a final agreement with Musk, and the specific development of electric vehicles will definitely depend on the two in the end.

I am looking for two people today mainly for another thing. This year we have seen that electric vehicles will become a trend in the development of automobiles, and we should also see another trend in the development of automobiles. "

Wang Chuanfu and Li Shufu glanced at each other, and did not think of the answer. Moreover, the last topic ended in this way. The two of them were quite confused. Facing the two doubtful eyes, Meng Qian gave the answer, "Unmanned driving."

Upon hearing the answer, the two suddenly realized.

"Google has officially deployed driverless vehicles this year, and backed by the US National Defense Advanced Research Projects Bureau, a large number of R&D personnel from the Bureau have gone to Google. In this field, I don't want to lag behind." Meng Qian stated clearly.

"What specific plans does Meng have?"

Meng Qian motioned for the two to watch the PPT presentation, "Our company has come up with a conclusion that sensors + high-precision maps + cloud computing + rational decision-making algorithms are the most likely solution for unmanned driving.

Therefore, if you want to develop unmanned driving, you need the corresponding lens, the corresponding C and S image sensor, the corresponding DSP digital processing chip, the corresponding millimeter wave radar, the corresponding laser radar and other hardware equipment, as well as a rational decision-making ability algorithm and A safe and high-speed cloud platform.

It is precisely because of this that for traditional car companies, driverless driving is actually a completely new field. Although the most important thing is still safety, traditional car companies are taking the functional safety route. In the field of driverless driving, functional safety is far from enough.

But is driverless a new industry? I don't think it is. When unmanned driving is truly mature, it will inevitably impact traditional car companies. If users trust in unmanned driving, the number of people willing to drive by themselves will inevitably decrease.

So today I just want to ask you if you are interested in participating in this car revolution with us. "

The two of them now understand why Meng Qian called them at the same time. Meng Qian wanted to engage in driverless driving and didn't want to put the bet on a traditional car company, so it was completely fine to call the two together.

"When President Meng is preparing to enter an industry, he must have been prepared?" Wang Chuanfu said with certainty of his understanding of Meng Qian.

Meng Qian smiled and motioned to continue watching the PPT, "As I said just now, unmanned driving requires lidar and millimeter wave radar. This is because lidar can accurately measure the relative distance between the edge of the object in the field of view and the device with accuracy. It can reach the centimeter level, and millimeter-wave radar can make up for the shortcomings of lidar that is not direct and fast.

Therefore, we have done a lot of research on lidar and millimeter wave radar. For unmanned driving, we have developed this 64-line lidar. Two people look at this dynamic picture.

The laser beam is emitted from the lenses on both sides, and after encountering obstacles, it can be caught by the middle lens. The receiver can judge the obstacles through processing and analysis.

All time information, control information, and received signals will be transmitted to the top motherboard for data analysis. The bottom rotation recorder can record the position and rotation information during rotation. All raw data is transmitted to the computer through the bottom data line.

As for the biggest advantage of this product, 64 beams are emitted radially in the vertical direction, which can cover an angle of 26° in the vertical direction and reach a detection distance of 100-120 meters. The error of detecting the position of the obstacle is about 10m. Rotate 10 times per second to achieve a horizontal 360° field of view coverage, and output up to 130,000 information points per circle. "

The two of them can still understand and understand this thing and are relatively easy to digest, but what Meng Qian said next made them feel a little embarrassed, "But in my opinion, our biggest advantage now is in the algorithm. .

As far as I know, several driverless companies, including Google, are using deep learning for driving training, deriving the output of the controller directly from the input of the sensor. However, as the founder of deep learning, I can basically confirm this depth. Learning is a wrong direction in the field of unmanned driving, because it belongs to correlation reasoning, not causal reasoning.

For example, people walk slowly on rainy days. The logic of this kind of deep learning is to walk slowly on rainy days, but it doesn’t know why they walk slowly on rainy days. Then if we don’t provide data on snowy days, a situation will arise. , Autonomous driving will slow down on a rainy day, but drive at a normal speed on a snowy day, and may even speed up due to other data.

This causal algorithm is a great hidden danger for driving safety, because there are too many unknown situations in the driving process that require the computer to make causal judgments.

So we need to introduce a new decision-making mechanism in the field of autonomous driving~www.ltnovel.com~ We have found such a mechanism, that is, Bayesian network, Bayesian network is a probabilistic reasoning system, Bayesian network in data processing In terms of event probability and event credibility analysis, it has a good classification effect. It has two decisive advantages: modularity and transparency.

The advantages of modularity are particularly important. For example, to update the gearbox of a car, when the gearbox is replaced, we don’t need to rewrite the entire transmission system, only need to modify the subsystem modeling the gearbox, and the rest can remain unchanged. .

As far as I know, the company that uses Bayesian networks to analyze a large amount of driving data is currently only our Dafeng Group.

And this is our big advantage. "

I don't know why, but Wang Chuanfu and Li Shufu's view of Meng Qian's two leading technologies is particularly normal, and there is not even a slight disturbance.

Meng Qian is actually very clear about the attitude of the two of them. Seeing that they have no intention of resisting, they directly pointed out the goal. In 2010, Dafeng Group will conduct at least 100,000 kilometers of unmanned driving experiments to actively seize the high ground of human driving technology.