Recently, the Ministry of Science and Technology has successively announced the special project information of the "14th Five-Year Plan" National Key R&D Plan, and the special "Automatic Driving Simulation and Digital Twin Test evaluation ToolChain" project for new energy vehicles declared by Chang'an University and Tencent and other units has been approved and successfully selected as the national "14th Five-Year" Key R&D Plan.
The "National Key Research and Development Program" of the Ministry of Science and Technology is one of the most influential and highest-level scientific research programs in the mainland at present, and has now become an important scientific and technological funding channel for the mainland to address major scientific and technological issues related to the national economy and people's livelihood and to break through the technical bottlenecks in the main fields of national economic and social development.
The "Automatic Driving Simulation and Digital Twin Testing and Evaluation ToolChain" project was successfully recognized by the Ministry of Science and Technology, which will accelerate the breakthrough of key technologies in the road permit and efficiency evaluation of high-grade automatic driving systems that adapt to the evolving traffic environment, create a complete tool chain for intelligent rating, defect identification and safety certification, and form an international core competitiveness technical support for mainland autonomous driving.
It is understood that the main objectives of the project have 4 levels:
Construct full-element, all-scenario high-fidelity modeling and real-time simulation software, develop scene generation technology and accelerate test cloud platform that integrates traffic flow characteristics;
Fully combine the advantages of actual site and virtual scene testing, and establish an online accelerated twin test system for virtual and real interaction;
Explore the coupling response relationship between the bicycle individual and the multi-controlled agent between the traffic in the loop test, and develop a high-precision vehicle traffic in the loop test system;
Research on the integration mechanism and assessment method of the toolchain, and improve the standard specifications.
The project focuses on 10 domestic autonomous driving testing and evaluation units, including Chang'an University and Tencent, and has formed a professional research team, which gathers leading enterprises and research institutes in the mainland automobile, transportation and other industries, and will provide complete testing technology support for mainland autonomous driving road permits, quality and safety assurance, traffic management, etc.
At present, Tencent's automatic driving digital twin simulation test platform TAD Sim (upgraded to 2.0) integrates accurate vehicle dynamics models, professional game engines, 3D reconstruction technology and virtual and real traffic flow technology, which can complete the automatic driving simulation test of all modules on the real vehicle such as perception, decision-making and control algorithms. TAD Sim continuously trains models to iterate on models by using real data, provides application services such as intelligent analysis and simulation testing, and builds a closed loop for rapid research and development, verification and upgrading of autonomous driving.
Previously, TAD Sim won the global new energy vehicle innovation technology and other simulation field awards, becoming the mainland's "strength faction" in the field of automatic driving simulation.
In terms of integrity, TAD Sim provides a full-stack toolchain that can be deployed in Windows, Linux and Web environments, and is an autonomous driving simulation system with a complete test and verification process of "data acquisition, scene modeling, scene automatic generation, model in the loop, software in the loop, cloud acceleration evaluation, hardware in the loop, and vehicle in the loop".
In terms of efficiency, TAD Sim cloud simulation technology supports parallel computing of more than 10,000 scenarios, and the running time is greatly reduced. At the same time, Tencent uses the traffic flow data of virtual reality to build a virtual simulation world at the city level, supporting thousands of autonomous vehicles and hundreds of thousands of traffic flow vehicles running at the same time, and the information between vehicles in the virtual city is synchronized in real time, ensuring the effectiveness and completeness of the test while being efficient, and opening up a new pure machine test method.
In terms of authenticity, TAD Sim has developed a full set of models including vehicle dynamics, sensors, traffic flow, map and scene editing, and supports the OpenX series and OSI international simulation standards, solving the problem that some core models of traditional simulation software rely too much on third parties. At the same time, tencent relies on its in-depth accumulation in high-precision maps, game technology, AI and other fields, and uses artificial intelligence algorithms to achieve high-precision and automated three-dimensional reconstruction of scenes. In addition, the simulation results of the dynamic model in the system are more than 95% consistent with the field experiment data to ensure the true validity of the industry-leading test.
The application of digital twin technology to the R&D and testing of autonomous driving can reduce the risk of road testing, improve the safety of the testing process, and greatly reduce the time and capital cost of testing, and improve the efficiency of development iteration. In addition, at the regression test level of the autonomous vehicle software OTA, digital twin simulation can effectively improve the test verification efficiency of intelligent driving software upgrades.
Tencent's digital simulation test platform for autonomous driving, TAD Sim, has previously cooperated with the National Intelligent Connected Vehicle (Changsha) Test Zone, the China Automotive Technology research center, the National Automobile Quality Supervision and Inspection Center (Hubei), the Traffic Management Science Institute of the Ministry of Public Security, the Shenzhen 5G+ Intelligent Network Test Demonstration Platform and other testing institutions, as well as a number of leading automobile companies at home and abroad, and launched real-time digital twin exploration and construction of traffic in scenarios such as smart high-speed and open urban roads.
In the field of smart transportation, combined with roadside sensing devices, Tencent has created a real-time digital twin system from perception, twin to user reach based on the automatic driving simulation system. The system uses Radar-Only to perceive and integrate high-precision maps, build holographic dynamic real-time semantic traffic scenes, each vehicle is driven by intelligent models, without any intervention, through 5G and other communication technologies to transmit the parameters of the physical world to the digital twin world in real time, forming a direct mapping of physical and virtual, directly reflecting the current traffic environment and traffic characteristics.
At any time, the operator can replace and add an autonomous vehicle to the virtual traffic flow in the twin system to verify the autonomous driving algorithm. The vehicle-road collaboration system becomes a 7x24-hour scene generator, all twin scenarios correspond to the real, real-time traffic environment one by one, and can be edited and modified, which not only ensures the true accuracy of the simulation environment, but also ensures the flexibility of testing, and can also provide accurate test scenarios for bad weather environments.
Tencent Smart Transportation will continue to take the opportunity of this special project to provide complete simulation testing technology support for mainland autonomous driving road permits, quality and safety assurance, traffic management, etc., and enhance the core competitiveness of mainland autonomous driving simulation testing in the field of international automation.