Tesla has released the Autopilot 2.0 system with "automatic driving function", and this system can cover almost all Tesla models. However, after the autopilot technology has just caused a number of fatal accidents, has the Autopilot 2.0 system now reached the five-level automatic driving ability? And should people still have confidence in this new technology?
Tesla has been able to achieve the fifth level of automatic driving
Tesla founder Elon Musk has announced that all new Tesla vehicles will be equipped with Autopilot 2.0, a hardware system with fully automatic driving functions. According to Tesla's official website, the autopilot hardware Autopilot 2.0 will be available for all Tesla models, including the latest Model 3, while the Model S and Model X with this new hardware are already in production.
Of course, this Autopilot 2.0 won't be available right away, even if you buy a new Model X now, you can't fully use the autopilot mode yet, because Tesla says he still needs to "by driving hundreds of people in the real world. Ten thousand miles to calibrate this new system."
It is reported that this new system will contain 8 cameras to cover the 360-degree visual range, and the monitoring distance to the surrounding environment can be up to 250 meters. The vehicle's 12 ultrasonic sensors complete the vision system, detecting and sensing hard and soft objects twice as long as the previous generation. The new enhanced front-end radar provides richer data around the redundant wavelengths, and radar waves can also be detected through heavy rain, fog, dust, and even vehicles in front.
Musk said that the new hardware will be fully capable of supporting Level 5 level autopilot, which means that the car can completely "drive the car".
At the same time, Musk also released a video content for the first time to show us the power of the so-called "Autopilot 2.0". The video shows that a Model X first automatically exits the parking lot, and after receiving the driver (the United States requires all autonomous vehicles to be equipped with a human driver ready to take over the vehicle at any time), including at intersections, highways, etc. The road runs on public roads. Finally, the car automatically finds the parking space to complete the parking after returning to the parking lot to put the driver down.
It should be said that it is amazing enough that a vehicle that does not have any strange devices around the body can be fully autonomous. After all, at this stage, Google (microblogging) self-driving cars also need to be equipped with many radars and sensors on the roof, and such a technical configuration is obviously not suitable for civilian use.
Musk even said: "When Tesla vehicles look for parking spaces, it will also confirm whether parking is allowed here, so Tesla will automatically avoid those disabled parking spaces."
Autopilot grading standard
As we all know, the automatic driving technology has a strict grading standard in the world, and the US Department of Transportation chooses the evaluation standard given by the Society of AutomoTIve Engineers. The main contents are:
Level 0: No automatic driving, the human driver has full control of the car and can be assisted by a warning or intervention system;
Level 1: Driving support, providing driving support for one of the steering wheel and acceleration/deceleration through the driving environment, and other driving actions are performed by the human driver;
Level 2: Partially automated, providing driving support for multiple operations in the steering wheel and acceleration and deceleration through the driving environment. Other driving actions are performed by human drivers.
Level 3: Conditionally automated, all driving operations are performed by the automatic driving system. According to system requirements, human drivers need to provide a response when appropriate.
Level 4: Highly automated, all driving operations are performed by an automated driving system. Depending on system requirements, human drivers do not necessarily need to respond to all system requests, including road and environmental conditions.
Level 5: Fully automated, all driving operations can be done autonomously by the autonomous driving system under all road and environmental conditions that human drivers can handle.
At present, the existing auto and Internet manufacturers are mostly concentrated in the second or third level in the autopilot technology, including the previous generation of Tesla Autopilot system that caused many autopilot accidents.
Therefore, Tesla claimed that the Autopilot 2.0 system jumped directly from the third to the fifth automatic driving is still a little worry. But Musk still believes that the autopilot system is actually much safer than people think. Although the media has been promoting the idea of ​​"automatic driving killing people" after the accident, Musk believes that this statement completely ignores the reality of 1.2 million car accidents caused by "man-made driving" every year.
Limitations of Tesla test video
As far as the video content released by Musk is concerned, we don't actually see any challenging road conditions in autonomous driving. The road test video that he released can even be said to have selected the best location in California. For example, the weather conditions in the video are very suitable, the road is flat, the road markings are clearly visible, and it is not obstructed by any obstacles, and the high-speed entrance and exit signs are also very clear.
Judging from the road conditions in the video, this road test is likely to be carried out in Palo Alto, but the actual road conditions in many other parts of the United States are not so ideal. In actual driving, we are likely to encounter many problems such as broken pavement, pits on the ground, blurred road markings, unclear signs, bad weather, etc., but Tesla’s video does not show it. How the latest autonomous driving systems will harness this road.
Judging from the actual experience of foreign media, at least the first generation of Autopilot is not able to perfectly control this road. For example, when the highway surface cannot be clearly identified by the system due to rain, the system will ask the driver to take over immediately.
Although Tesla has made it clear that it needs to "calibrate the new system by driving millions of miles in the real world", it is clear that there is still a lot of autonomous vehicles on the public road. Quite a distance.
Tesla's adventure
Compared to many old American car manufacturers, Tesla can only be regarded as a young latecomer, but the company's investment in autonomous driving technology and its achievements are enough to surpass any manufacturer.
Take Google, although Google has also invested huge resources in the field of autonomous driving, but because the company is only a technology company, it can only rely heavily on other manufacturers to promote autonomous driving technology, but also lacks similar Tesla. Such an OTA system upgrade mechanism.
More importantly, Tesla is more adventurous than traditional car companies and other Silicon Valley technology companies.
Mike Ramsey, research director at Gartner, a US consulting firm, said: "Teslas doesn't mind putting the product on the market before it's fully completed, but it's not what Google, GM and other vendors are willing to do. Things, they think that products can only be put on the market if they meet the 'perfect' standard."
Fei-Fei Li, the director of the AI ​​research office at Stanford University and a Chinese professor, believes that Tesla's first deployment of autopilot system hardware for its models is a strategic plan for the future.
"The competition about autonomous driving technology has already begun, but I am afraid that there will still be a long period of time after actually running this track."
It should be noted that Tesla did not implement a Lidar Lidar-based solution in its models, which is considered by many other manufacturers to be a necessary configuration for autonomous driving. But what many people don't realize is the high cost of Lidar lidar. The cost of some high-end Lidar lidars even reaches $700,000, even more than the price of a Tesla.
With no Lidar lidar configured, Tesla effectively controls vehicle costs, and the price of its new autopilot feature kit is well controlled at $8,000. But the downside is that Tesla's autopilot system may not be as reliable in some cases as the model equipped with Lidar Lidar, which was recently occurred by Joshua Brown, the owner of Tesla. A car accident may be the best example.
"They are risky, but they are also revolutionary enough for auto companies," Li Feifei said.
It should be said that Tesla's adventurous entrepreneurial spirit directly led to its parting with long-term partner Mobileye. Mobileye co-founder and CTO announced at the previous earnings conference: "EyeQ3 chip will be the last cooperation between Mobileye and Tesla. However, we will continue to support and maintain Tesla's existing autopilot product project Autopilot. This includes recent major feature upgrades, including anti-collision response optimization, optimized auto-steering, etc. But on the hardware side, we will not have any updates to Tesla."
For most people, the fuse that caused Mobileye and Tesla to break up is the death of the Tesla Autopilot system in May this year. Mobileye and Tesla have different opinions on this serious accident. Mobileye believes that their product features are inherently limited. It is Tesla's radical openness and publicity that causes the use of the owner to exceed the functional limit, while Tesla emphasizes that the cause of the accident is mainly the recognition error of the camera and radar.
But what is certain is that if Tesla's slightly radical technological advancement strategy turns out to be successful, then the voice of doubt about the company will soon vanish.
"If this method works, then all manufacturers will follow suit. They must do this, otherwise they will be eliminated by the market." Ramsey finally said. (General / Tom)
For the 22kV Oil Immersed Power Transformer, we can produce capacity upto 420MVA. We use the best quality of raw material and advance design software to provide low noise, low losses, low partial discharge and high short-circuit impedance for power transformer.
Our power transformer are widely used in national grid, city grid, rural grid, power plant, industrial and mining enterprise, and petrochemical industry.
220Kv Transformer,220Kv Power Transformer,High Quality Power Transformer,Oil Immersed Transformer
Hangzhou Qiantang River Electric Group Co., Ltd.(QRE) , https://www.qretransformer.com