2020 China’s self driving simulation Blue Book From China EV100

RecordTrend.com is a website that focuses on future technologies, markets and user trends. We are responsible for collecting the latest research data, authority data, industry research and analysis reports. We are committed to becoming a data and report sharing platform for professionals and decision makers. We look forward to working with you to record the development trends of today’s economy, technology, industrial chain and business model.Welcome to follow, comment and bookmark us, and hope to share the future with you, and look forward to your success with our help.

The following is the 2020 China’s self driving simulation Blue Book From China EV100 recommended by recordtrend.com. And this article belongs to the classification: Automobile industry, research report.

Simulation test is very important for the safe landing of automatic driving. According to the research of RAND Corporation, if the automatic driving algorithm wants to reach the level of human driver, it needs at least 17.7 billion kilometers of driving data to improve the algorithm. If a fleet of 100 automatic driving test vehicles is equipped, the road test is carried out 24 hours a day and the average speed is 25 miles (40 kilometers) per hour. It will take more than 500 years to complete the target mileage.

In addition, the lack of automatic traffic regulations and insurance claims mechanism also restricts the wide range of automatic driving vehicle testing. Due to the fact that the automatic driving vehicle can not guarantee absolute safety, our government maintains a cautious attitude towards the open automatic driving road test. It is difficult to satisfy the exuberant test demand of the automatic driving vehicle only by relying on some open roads and intelligent network test area.

At present, simulation test based on scene library is an important way to solve the problem of lack of driving test data. Simulation test is mainly through the construction of virtual scene library to realize the closed-loop simulation test of automatic driving perception, decision planning, control and other algorithms. Scene library is the basis of automatic driving simulation test. The higher the coverage of scene library to the real world, the more realistic the simulation test results are.

Different stages of automatic driving vehicle development require different scenario libraries.

According to the data of the blue book, about 90% of the automatic driving algorithm test is completed on the simulation platform, 9% in the test field and 1% in the actual road test. With the improvement of simulation technology and the popularization of application, the industry aims to achieve 99.9% of the test volume through the simulation platform, 0.09% of the closed test is completed, and finally 0.01% of the real road test is carried out, which makes the research and development of automatic driving more efficient and economical.

At the press conference, Zhu Xichan, director of the Institute of automotive safety technology, School of automotive, Tongji University, said: “without a virtual simulation platform, the development of intelligent networked vehicles can’t be realized at all. In order to realize China’s dream of moving from a big automobile country to a powerful automobile country, the virtual simulation platform as a core technology must be autonomous and controllable.”. China is the world’s largest automobile production and consumption country. As one of the most important core technologies in the development of the autonomous driving vehicle, simulation software must realize its own research and development to take the leading position in the international competition. The total number of simulation software enterprises and units in the United States and Germany accounts for more than half of the global total. Chinese enterprises are still in the catching up stage in this field.

Based on the current situation, technology companies, auto driving solution providers, simulation software enterprises, universities and scientific research institutions are all engaged in the construction of virtual simulation platform. Science and technology companies start relatively late in simulation, and have less experience in vehicle function exploration, but have the advantages of big data and strong software development ability. At present, automatic driving simulation technology companies mainly include Tencent, Baidu, Huawei, Ali, etc.

Taking Tencent as an example, based on the technology accumulation in the fields of map, game, cloud computing and artificial intelligence, Tencent’s automatic driving virtual simulation platform TAD is developed Sim can realize automatic scene generation and cloud high concurrency test, and improve the efficiency of automatic driving test verification. At present, Sim has cooperated with intelligent network joint test sites in Changsha, Xiangyang, Shenzhen and other places in the field of automatic driving test.

Tencent automatic driving simulation platform TAD sim (Tencent autonomous driving simulator) was released in 2018. It is an automatic driving simulation platform combining virtual reality with reality, online and offline integration, which combines professional game engine, industrial vehicle dynamics model, virtual reality integrated traffic flow and other technologies. In order to achieve a high degree of scene restoration, Tencent uses its own experience and technology in the game field, including scene restoration, atmospheric system, sensor simulation, physical engine, agent AI, cloud game technology, MMO synchronization and other game technologies.

In June 2020, TAD SIM 2.0 was released, and the architecture was optimized and upgraded on the original basis. The data transmission capacity and acceleration ability were greatly improved, and the resource consumption was reduced by 30%. At present, there are more than 1000 scene types in the scene library, which can generate more than 10000 times of rich scenes, and has the test ability of more than 10 million kilometers per day.

At present, Tad Sim is cooperating with national intelligent network vehicle test area in many places, national ministries and commissions, as well as domestic leading automobile enterprises, including cooperating with national intelligent network connection (Changsha) test area, reconstructing the geographical panorama of the test area with virtual simulation technology, supporting the intelligent network connected vehicle simulation test, assisting the digital twin automatic driving evaluation system of Xiangyang Da’an automobile testing center and Shenzhen intelligent automobile testing center The construction of network connected transportation test and demonstration platform, the implementation of virtual reality combined simulation test, the acceleration of automatic driving R & D landing, and the promotion of intelligent transportation construction and operation upgrading.

If you want to get the full report, you can contact us by leaving us the comment. If you think the information here might be helpful to others, please actively share it. If you want others to see your attitude towards this report, please actively comment and discuss it. Please stay tuned to us, we will keep updating as much as possible to record future development trends.