Vol 3 Chapter 2264: Over-the-limit obstacle course flight test

"go!"
With a command, the first Man-Eater Fly Micro-Attack UAV in the swarm array of Man-Eater Fly Micro-Attack UAV broke away from the swarm and flew towards the arranged obstacle passage at high speed.
The entire obstacle course is very narrow. In fact, it is separated by wooden boards and acrylic boards. The narrowest part is only a few centimeters wide and requires continuous turns. In addition, the light transmittance of the acrylic sheet is hesitant, which greatly increases the difficulty of detection by the sensors on the drone.
Speed ​​slowed as the first man-eating fly micro-attack drone entered the obstacle test tunnel. However, the speed is still very fast. The entire drone fuselage shuttles quickly in a small space, avoiding obstacles in all directions, following the 'Z'-shaped flight route, and advancing in the narrow obstacle test channel.
However, the man-eating fly micro-attack drone did not fly for long in the obstacle test channel. When passing a small acrylic obstacle, the tiny fan blades on the drone were hung with acrylic plates. The edge, causing the drone to lose control, was directly installed on the other side of the board, and crashed directly into the obstacle test channel.
Coco, did the flight data transfer back? Wu Hao asked.
A window appeared on the screen on the side, with Coco's avatar in it, and it reported: "Sir, the flight data has been returned to the database and shared with other drones synchronously through the cluster control system data link."
Wu Hao nodded when he heard the words, and waved his hand with a smile: "The second test begins!"
OK As Coco responded, the second Man-Eating Fly micro-attack drone flew out of the swarm array and began to fly into the obstacle test channel. After having the flight data of the first UAV, the speed of the UAV in the previous obstacle crossing flight is significantly faster. Obviously, it refers to the flight data of the first UAV.
This is also a major feature of the cluster control system, that is, resource sharing, all detection data can be shared, including flight lines and so on. The previous drone will transmit the detected related obstacles to the swarm array, which also lets other drones know what the obstacle section here looks like, so the subsequent drones can follow along. Follow the flight path of the UAV ahead.
Of course, it is not a complete follow-up and imitation. These flight lines are only for reference, which can greatly reduce the detection data processing capacity of the drone, so it can fly faster in narrow passages.
This does not mean that it completely abandons the detection of surrounding environmental data information, because in reality, even if the flight distance of these drones is short, the surrounding environment may change during this interval, which will lead to people in the same flight. The position of the obstacle, the angle changes.
At this time, if you follow the flight path of the aircraft in front, it is very likely to hit an obstacle and crash.
Especially this kind of micro drone is more susceptible to changes in the surrounding environment.
A very simple example is the swaying of the branches and leaves of trees and plants in the wind. Large drones may not need to consider these, but tiny drones must. It is likely to be a leaf, which can stop the entire drone.
Soon, the second second drone crossed the wreckage of the first drone and began to continue to fly forward, but compared with the previous flight speed, the current flight speed has dropped significantly.
The drone flew forward for about one meter, and because it could not turn in time, it was directly mounted on the obstacle, causing the entire drone to be crashed.
Then the third drone broke away from the swarm array and began to continue testing.
Doing so is not playing, nor is it wasting, but training the intelligent flight control system of the drone. Through a large amount of obstacle clearance flight data, the flight control obstacle avoidance performance of the UAV can be greatly improved, especially the obstacle avoidance performance in such a small space.
In fact, before that, they had already accumulated a wealth of drone flight data. After all, they were the first to start with drone technology, and they have developed along the way, and it can be said that they have accumulated a lot of experience in this area.
However, these are all large, medium and small drones, and even the smallest drone they made is much larger than the current one.
Therefore, the flight control data accumulated by those drones before may not necessarily be applicable to this kind of micro drone. Some of them can be used for reference, and others require drones to fly out autonomously. Through the continuous accumulation of flight data, the intelligent flight control system of the UAV can learn how to deal with the same or similar situations.
"Gene Era"
In fact, the entire testing process does not require Wu Hao to participate at all, and can be handed over to others. Of course, there is a more convenient and convenient method, which is to hand over the responsibility to Cocoa and the intelligent simulation robot. It only needs to wait for the experimental data results.
However, there are some things that artificial intelligence cannot understand. Although they are smart, they cannot have as many divergent creative thinking as humans~EbookFREE.me~ Sometimes too accurate data, or too rational judgments are not conducive to innovation. In fact, many innovative inventions are inadvertently made by accident or even by mistake. However, artificial intelligence does not care about these mistakes or instinctively filters them and pursues successful results.
They can be very rational, but not emotional. This is the biggest technical problem of artificial intelligence technology in the world. How to make them perceptual is the key to making them self-conscious.
And Wu Hao obviously broke through these, using what was in his brain to create Cocoa. However, due to the limitations of the current comprehensive technology level in the world, he couldn't make full use of the movements in his head, and his intelligence improved little by little.
For example, from the birth of Cocoa to the present, in fact, the performance of Cocoa has been continuously improved. Compared with the beginning, it is now smarter and closer to people. Otherwise, Chen Keren would not have been in the company for so long.
Now, although he directly participated in the entire experimental process, he actually did not need to be with him personally. He only needed to issue an order, and Cocoa would come to complete it according to its instructions. Of course, some experiments still require him to operate it himself. Coco is very smart and understanding, but he can't fully understand what he means.
And many things are said and done as two feelings, just like there is an old saying, "you can only understand what you can understand". Some things can be thought of and made by the brain, but how to express them accurately requires thinking.
This is also the reason why it is difficult to write many papers about the results. You have to express the results intuitively and accurately, and not allow the readers to distort them.