"For example, we have improved the accuracy of the detection sensors mounted on the autonomous driving system. First, we have improved the original lidar, which greatly extends the range of the lidar.

As we all know, the detection distance directly affects the response time of the system for the identification and early warning of obstacles. The longer the detection distance, the more data information can be detected, which is beneficial to improve the overall security.

In addition, the longer the detection distance, which means that the formal speed of the vehicle can be greatly improved. In the past, possibly limited by detection technology, self-driving cars had to be controlled within a speed range beyond which the self-driving system would automatically exit and let the driver take over.

And our next-generation lidar can detect longer distances, basically three to four times the detection distance of these lidars currently on the market. This also means that our autonomous driving system can detect obstacles that may appear in front of them hundreds of meters away, so as to make planning ahead of time instead of temporarily reacting in front of them.

At the same time, it also means that the autonomous driving technology under the blessing of a new generation of lidar can be applied to faster vehicles or other vehicles. For example, high-speed rail, its speed can reach 350 kilometers, and some can even reach 400 kilometers. With such a fast speed, the time for the driver to reflect is very short. If this system can be applied, the high-speed rail will detect the road conditions ahead more accurately and respond more quickly during high-speed driving. This helps to reduce some accidents and problems that occur because people are limited by various conditions and react too slowly. "

Speaking of this, Zhou Yonghui changed his breath, and then continued: "In addition to the detection distance, the scanning frequency and detection resolution of the lidar are also the basis for measuring the quality of the lidar.

This time, we have made great efforts in these two aspects, so that the performance of these two aspects has been greatly improved.

The so-called scanning frequency refers to the detection speed of the same object or the surrounding environment within a period of time. The higher the scanning evaluation rate, the more detailed and timely the information of the surrounding environment can be obtained by lidar detection, and the small changes in the surrounding environment can be detected in real time.

The difference in scan frequency may not make much difference in low speed processes, but in high speed and ultra-high speed environments, scan frequency is critical. The higher the scanning frequency, the more detailed the detection of high-speed moving objects, so that more detailed shapes of the surrounding high-speed moving objects can be known, so as to tell the automatic driving system to process and avoid.

As for the detection resolution, it refers to the ability of lidar to detect tiny objects.

One thing everyone should know is that the objects detected by lidar are not what we see, but dot matrix clouds. The contour shape of the object can be known by the distance between the contour surface of the object and the lidar.

The higher the detection resolution, the more detailed the outline of the detected object we can know.

The current LiDAR technology on the market can achieve high ranging resolution for short-range targets, but its resolution will also decrease sharply as the distance of the detected object increases.

Therefore, in order to achieve longer-distance detection, it is not just as simple as increasing the laser power, but also requires essential improvements to the ranging core.

These lidar products on the market have very low detection resolution for long-distance targets and environments, which will bring some problems to vehicles.

As for our new generation of lidar, the detection resolution has been greatly improved, and its detection accuracy of 100 meters can reach the centimeter level. What does it mean, that is to say, we can identify a small pit on the ground or a falling nail at a distance of 100 meters, so as to avoid it in advance. "

This is too exaggerated. Hearing Zhou Yonghui's introduction, someone at the scene couldn't help but exclaim.

Hehe, Wu Hao and the others laughed when they heard the words. They were indeed a little surprised by such a high detection accuracy.

"It's a bit exaggerated, but this is the result of our actual test, and there is no adulteration. And the detection accuracy is very high. The size outline of the target object we detected is basically the same as the size outline of the actual object. There is a deviation." Zhou Yonghui replied with a smile.

After talking about this, Zhou Yonghui glanced at Wu Hao, and then continued: "In order to improve the performance of the new generation of laser radar, we have also greatly improved the anti-interference of the new generation of laser radar.

Especially in the detection rate of objects of different colors, as well as the anti-interference for ambient light and other light, have been greatly improved.

The detection of lidar originally uses the light emission to hit the object to be measured, reflected back and accepted, and then the time between going back and forth, so as to obtain the distance between the lidar and the detected object, and then the object in front can be known through countless rays of light. The size is reduced to information.

Then this brings about a new problem. We all know that objects of different colors and materials have different light reflectances, so the detection values ​​obtained are naturally very different.

For example, dark objects, which are different from white objects have a high reflectivity. Dark objects can absorb most of the light ability. It is obviously unrealistic to make lidar have the same detection power for dark objects as white objects. .

So how to balance the direct detection differences of objects of different colors~lightnovelpub.net~, if the influence of dark objects on lidar detection is reduced, this is also the focus of our research.

Fortunately, Huangtian pays off. After our continuous research and optimization, we finally improved our sensor technology, optical adjustment, and optimized processing algorithms, which greatly improved our performance in this regard. But from this point, we can beat a lidar product on the market.

In addition, there is the anti-interference of ambient light, which is also the focus of our research.

Lidar uses light to detect objects, so it is naturally affected by other light. For example, direct sunlight, artificial lights, and other ambient light will affect the detection performance of lidar.

Therefore, we have also made great efforts in this regard. On the one hand, we have improved the laser light source in lidar to make it as different as possible from natural light. On the other hand, it is calculated through intelligent processing algorithms to filter out the noise of other light sources except lidar, so that the obtained laser detection data is clearer and more accurate. "