提供永久免费的API接口，查看更多API接口，如果您有其他免费API资源，请联系我们，造福人类。

定制开发，免费评估，免费咨询，价格便宜，售后保障，前往开发服务中心或联系开发客服中心

Use wechat scan QR code to share with friends and circle of friends. Recently, the head of Tesla's artificial intelligence explained the reason at a meeting, saying that the vision system developed by Tesla can completely replace other sensors. Tesla, the electric car manufacturer, has its own unique way of developing autonomous driving features. In a speech at the computer vision and pattern recognition conference, Andrej karpathy, Tesla's senior director of artificial intelligence, explained why < p > < / P > < p > at present, the automatic driving function is actually the sum of all personal safety systems in today's cars. Many new cars are equipped with automatic braking, adaptive cruise control, lane keeping and anti mistakenly stepping on the accelerator and other functions. The main challenge for car manufacturers is to integrate all these functions into a more efficient and reliable system than human beings The first problem is perception. The vehicle must be able to understand its surroundings in order for these subsystems to work at the right time. Vehicle perception is also the biggest difference between Tesla and other auto manufacturers. Musk recently chose not to install radar sensors in Tesla cars, but to install only optical cameras to sense changes in the surrounding environment < p > all other car manufacturers use optical cameras, in vehicle radars and lidars to collect environmental data. Because lidar is very expensive, it is relatively rare; And car manufacturers widely use low-cost car radar < p > "radar is just a crutch," Andrej karpathy told the conference < p > car manufacturers often use on-board radar to measure relative speed and distance, but Tesla believes that optical cameras can do the same. The difference between the onboard radar and the optical camera affects the improvement of Tesla's automatic driving function, so Tesla decided to focus on improving the camera system "The vision system we've built over the past few years is so good that we can leave other sensors far behind," kapasi said < p > after perceiving or collecting environmental data, we begin to calculate and make decisions. Most of kapasi's speech was about Tesla's artificial intelligence and computers < p > these sound quite complicated. If you are not familiar with 3D convolution, sensor fusion, neural network and other professional terms, then it is impossible to understand Tesla's decision-making method < p > kapasi did not explain what achievements Tesla had compared with other companies in the field of automatic driving < p > APTIV, a provider of auto parts and technology, has actually driven and simulated billions of kilometers through advanced safety systems. APTIV, which also has thousands of safety engineers, can provide a driving aid system similar to Tesla autopilot directly to any car manufacturer. But the company also rarely talks about details However, Tesla may have the advantage of scale. The company already has millions of electric vehicles to test, and the vehicles it has sold are learning to test. Kapasi said that Tesla's neural network works in "shadow mode" on Tesla cars, predicts what drivers will do in the background, and enhances the robustness of automatic driving software < p > in the third quarter of 2020, Tesla CEO musk said that fully automatic driving technology will achieve "the largest asset value growth in history"

, for example, an autopilot can carry other people around the car when the owner is working or sleeping, making money for the owner. Recent analysis estimates that Tesla's current share price is $650, of which $100 to $200 are based on Tesla's expectation that it will provide drivers with a higher level of automatic driving function by the end of this year. If Tesla can make real progress in confirming the safety of the autopilot system, other auto companies may compete to imitate Tesla to sell their own autopilot function. A huge innovation field and potential profit source will emerge from this However, at present, investors seem to be waiting for specific progress. Tesla's shares have fallen about 12% this year, behind the gains of the S & P 500 and the Dow Jones industrial average（ Chen Chen) < / P > < p > 1

2023-03-22 10:04:37