Hard-core interpretation of Jidu Automobile Robot Concept Car, is the dual lidar solution enough?

Bitauto original? On April 18, Jidu officially released the design details of the front part of the first automotive robot concept car. The design of the headlights and lidar on the front cover are clearly visible. At this point, Jidu’s pioneering car front cover and forward dual lidar autonomous driving technology solutions were exposed for the first time.

Seeing this plan made me sigh that not only do the number of laser radars need to be large, but their positions must also be unique enough, otherwise there is really nothing new at all. This shape first reminds me of the folding headlights of the AE86. It is reported that Jidu’s mass-produced model lidar will also adopt this method of revealing and hiding. As for whether it is lifting or folding, it has not yet been announced.

But the nice thing is that compared with those that are placed on the "head" or embedded in the front of the car, this shape has a retro style, as if it is a combination of the future and the past, the most cutting-edge. Technology is presented to us in a retro form, which is quite visual impact.

What will we do next around the establishment of Jidu for more than a year? This media communication meeting also revealed the latest developments and provided a popular science analysis of the technology. I hope that everyone will have a more comprehensive and in-depth understanding of the Jidu Automobile jointly created by Baidu and Geely.

01? More than 400 days after its establishment, what has Jidu done intensively?

Jidu is an automotive robot startup founded by Baidu and strategically invested by Geely. The company was officially established in March 2021, with Xia Yiping serving as CEO. Seeing this background, we know that Jidu was born with a silver spoon in its mouth. With the endorsement of the Internet giant Baidu and the domestic automobile leader Geely, Jidu attracted a lot of attention from the beginning. In addition, it was abandoned at the beginning. The new concept "car robot" launched by the company seems to be creating a smart electric vehicle that is disruptive in form and experience.

Where is the subversion? In summary, there are three points: 1. Free movement 2. Natural communication 3. Self-growth. Free movement is easy to understand, that is, this car robot can achieve L4 level autonomous driving functions, covering all high-level autonomous driving scenarios, truly freeing humans to hand over the control of the car to intelligent hardware devices; secondly, natural communication means voice and semantic interaction , barrier-free communication, making your car your intimate partner and making the car more humane. The complicated physical buttons in the past will no longer exist. You can talk to the car at any time to realize any functions you want; the third point of self-growth is It is constantly iterated and upgraded based on the habits of drivers and passengers, so that your car understands you better and helps you deal with various road conditions like a personal butler.

We know that the development cycle of a traditional car takes three years, but how did Jidu shorten the time from design, development to final mass production to less than two years? In fact, a very important point is the decoupling of software and hardware. The software algorithm of the vehicle, the electronic and electrical architecture of the vehicle, and the vehicle body and chassis are separated and developed to achieve dual-track parallelism. Even before the development of intelligent software systems, configuration, greatly improving R&D efficiency.

We introduced earlier that Jidu’s background is Baidu and Geely, so in terms of the body of traditional vehicles, Jidu’s car robot will be built using Geely’s SEA vast platform; at the level of intelligent brain, Baidu With rich accumulation of autonomous driving data and experience in research and development of smart cockpits, Jidu’s development pace will be several times higher than that of other car companies. It can be said that we are standing on the shoulders of giants.

According to the name of Jidu, this carrier that carries the brain and body is Jidu SIMUCar (Software Integration Simulation Car), which has been iteratively upgraded to version 2.0.

Let’s take a look at what Jidu has done intensively in the more than 400 days since its establishment?

On March 2, 2021, Jidu Automobile Co., Ltd. was officially established, and Jidu officially started the research and development of automotive robots.

On June 1, 2021, Jidu held its first press conference since its establishment to describe the positioning and planning of Jidu Automobile.

On June 10, 2021, photos of the clay model of the first Jidu automotive robot were exposed.

On July 7, 2021, Baidu founder Robin Li visited Jidu and participated in confirming the design of Jidu’s first product.

In August 2021, Jidu and Continental Group have cooperated with Hesai Technology to jointly promote the implementation of smart car robots. The first automotive robot will be equipped with Hesai Technology’s lidar

On September 24, 2021, SIMUCar was launched to develop front-end autonomous driving and smart cockpits.

On November 29, 2021, it signed a contract with Baidu and Qualcomm to launch the first mass-produced model in China using the 4th-generation Snapdragon automotive digital cockpit platform-8295.

On December 31, 2021, Jidu successfully integrated intelligent driving in high-speed and urban areas.

At the beginning of 2022, Jidu launched brands including the brand logo "Pixel-J", JIDU AI-Purple, and the exclusive "language" (ROBO Font) for car robots. Vision.

At the 2022 CES show, it was announced that NVIDIA’s autonomous driving chip Orin will be used. This chip will also be installed on the “Sanxian” ACU domain controller developed by Apollo.

Until now, ROBODAY, the first large-scale brand conference originally planned to be held in April, will be postponed due to force majeure. Previously, Jidu has announced that it will release its first automotive robot concept car in 2022 and debut it at this year’s Beijing Auto Show. Its first mass-produced automotive robot will be launched and delivered in 2023. It will have high-level autonomous driving capabilities and can bring users a high-level autonomous driving experience in multiple scenarios. At present, Jidu has started the research and development and pre-research of subsequent models, and its second mass-produced car is expected to be released at the Guangzhou Auto Show at the end of this year.

From this timetable, we can see that Jidu has indeed been racing against time this year. Although it started late, Jidu has innate advantages and acquired efforts. Therefore, in this wave of Internet car manufacturing, , Baidu seems to be the first to hit the mark.

02 Jidu’s intelligent driving technology solution is exposed for the first time. Are dual lidars enough?

Lidar is a cliché. We have popularized the working principle of lidar and its importance to current autonomous driving more than once. Various car companies are also making full efforts to achieve quantitative results. Advantages, and even more so with the slogan that if the number is less than a few, it is not necessary to talk about it. This trend of "involution" of lidar seems to be gradually becoming popular. However, the strategy of this concentration is relatively rational. Two LiDARs are installed on the vehicle, which not only achieves safety redundancy but also takes into account cost control. Let’s talk about what was said at this communication meeting. Two LiDARs Is it enough?

First of all, Dr. Wang Weibao, the person in charge of Jidu Intelligent Driving, shared the latest progress of Jidu’s automotive robots. Jidu SIMUCar (Software Integrated Simulation Prototype Car) has been iteratively upgraded to version 2.0. Its autonomous driving system has added lidar sensors and is implemented with Jidu’s self-developed high-end autonomous driving intelligent architecture JET1.0 (Electronic and Electrical Architecture SOA) Fusion. In terms of hardware, NVIDIA Orin, the world's highest computing power vehicle chip, and Hesai AT128 semi-solid-state lidar have been put on the vehicle and participated in the test of the intensive autonomous driving system. This means that Jidu’s high-end autonomous driving technology solution for mass production, based on Apollo’s unmanned autonomous driving capabilities, has been fully exposed for the first time.

It is worth mentioning that the pure vision and lidar autonomous driving solutions currently being tested and developed in the SIMUCar2.0 stage are independent dual systems and can achieve "true redundancy" after mass production. Compared with traditional solutions, Jidu’s two autonomous driving solutions back up and complement each other. The two solutions can both drive themselves efficiently and collaborate efficiently.

Let’s talk about the key point of lidar. We mentioned earlier that the location of this arrangement is very unique and innovative. So what are the specific parameters and performance of lidar, and can it help Jidu Automotive Robots truly achieve safety redundancy? Woolen cloth? The two lidars carried by the Jidu Automobile Robot are the AT128 from Hesai Technology. This lidar not only has a super range measurement capability of 200 meters (@10 reflectivity), but also has a point frequency of more than 1.53 million per second. points, reaching a global high resolution of 1200x128. Every detail can be clearly depicted on the point cloud, providing powerful perception capabilities for the assisted driving system.

Back to the question of whether two lasers are enough, the point cloud field of view of dual laser radars is wider and safer. Compared with the 120-degree FOV of a single radar design, dual radars on the front of the car can achieve a horizontal FOV of 180 degrees. Coverage, in driving scenes such as "ghost probes" and obstructions on the left and right, the ability to identify pedestrians or obstacles crossing the left and right is stronger. Secondly, the recognition of key areas of the vehicle is more accurate. In the 60-degree FOV area directly in front of the vehicle, the dual lidar can double the overlap, resulting in more point cloud data on the target and higher recognition accuracy. Third, in terms of redundant safety for high-level autonomous driving, dual lidars can be mutually redundant and more reliable than a single lidar solution.

lt;img class="imgborder" src="http://image.bitautoi