Summary of 7 major domestic and foreign autonomous driving simulation platforms

Before self-driving cars can be truly commercialized, they need to undergo a large number of road tests to meet commercial requirements. Using road tests to optimize self-driving algorithms consumes too much time and cost, and open road testing is still subject to regulatory restrictions. It is difficult to reproduce extreme traffic conditions and scenarios, and there are hidden dangers in testing safety. Currently, self-driving simulation testing has been widely accepted by the industry. About 90% of self-driving algorithm testing is completed through simulation platforms, 9% is completed on test sites, and 1% is completed through actual road testing.

In order for the simulation platform of autonomous driving to actually play a corresponding role in road testing of autonomous driving, it must have several core capabilities: true restoration of test scenarios, efficient use of road data to generate simulation scenarios, large-scale parallel acceleration on the cloud, etc., so that simulation testing can meet the closed loop of autonomous driving perception, decision-making planning and control of the full stack algorithm. Currently, entities including technology companies, car companies, autonomous driving solution providers, simulation software companies, universities and scientific research institutions are actively engaged in the construction of virtual simulation platforms, and it is believed that in the near future, it will play an important role in promoting the commercialization of autonomous driving.

This article will guide readers through the seven most famous autonomous driving simulation software platforms at home and abroad.

PreScan

PreScan is a car driving simulation software product of Siemens. Prescan is a simulation platform for developing ADAS and intelligent car systems based on physical models. It supports the development and application of various application functions such as cameras, radars, lidars, GPS, and V2V/V2I vehicle-to-vehicle communications. PreScan is based on the MATLAB simulation platform and is mainly used for simulation software for (ADAS) automotive advanced driver assistance systems and unmanned autonomous driving systems. It includes a variety of intelligent driving applications based on radar, cameras, lidars, GPS, V2V and V2I vehicle/vehicle-to-road communication technologies. It supports multiple usage modes such as model-in-the-loop (MIL), real-time software-in-the-loop (SiL), and hardware-in-the-loop (HiL).

Prescan consists of multiple modules, and its use is mainly divided into four steps: building a scene, adding sensors, adding a control system, and running a simulation.

Scene building: PreScan provides a powerful graphics editor that allows users to build rich simulation scenes using road segments, basic component libraries including traffic signs, trees and buildings, traffic participant libraries including motor vehicles, bicycles and pedestrians, and modify weather conditions (such as rain, snow and fog) and light sources (such as sunlight, headlights and street lights). The new version of PreScan also supports the import of high-precision maps in OpenDrive format to create more realistic scenes.

Add sensors: PreScan supports a wide variety of sensors, including ideal sensors, V2X sensors, LiDAR, millimeter wave radar, ultrasonic radar, monocular and binocular cameras, fisheye cameras, etc. Users can add them according to their needs.

Add control system: You can build a control model through MATLAB/Simulink, or perform closed-loop control with third-party dynamic simulation models (such as CarSim, VI-Grade, dSpace ASM's vehicle dynamics model).

Running experiments: The 3D visualization viewer allows the user to analyze the results of the experiment and also provides the ability to generate images and animations. In addition, interfaces using ControlDesk and LabView can be used to automatically run scenarios for experimental batches and run hardware-in-the-loop simulations.

CarMaker

Carmaker, as well as the related TruckMaker and MotorcycleMaker, are dynamics, ADAS and autonomous driving simulation software launched by the German IPG company. Carmaker is first of all an excellent dynamics simulation software that provides accurate vehicle body models (engine, chassis, suspension, transmission, steering, etc.). In addition, Carmaker has also created a closed-loop simulation system including vehicles, drivers, roads, and traffic environments.

IPG Traffic: It is a traffic environment simulation tool that provides a variety of traffic object models (vehicles, pedestrians, road signs, traffic lights, road construction buildings, etc.). It can simulate the real traffic environment. The test vehicle can identify traffic objects and trigger actions accordingly (for example, a speed limit sign can trigger the vehicle to slow down accordingly).

IPG Driver: An advanced, self-learning driver model that can control the vehicle under various driving conditions, such as starting uphill, parking in a garage, and steering in a drift. It can also adjust the driving strategy based on the vehicle's power characteristics (drive mode, gearbox type, etc.), road friction coefficient, wind speed, and traffic environment.

As a platform software, CarMaker can be integrated with many third-party software, such as ADAMS, AVLCruise, rFpro, etc., and can use the advantages of each software for joint simulation. At the same time, the hardware supporting CarMaker provides a large number of board interfaces, which can be easily used for HIL testing with ECU or sensors.

CarSim

CarSim, as well as the related TruckSim and BikeSim, are powerful dynamics simulation software developed by Mechanical Simulation, and are widely used by OEMs and suppliers around the world. CarSim is for four-wheeled vehicles and light trucks, TruckSim is for multi-axle and dual-tire trucks, and BikeSim is for two-wheeled motorcycles. CarSim is a whole vehicle dynamics simulation software that simulates mainly from the perspective of the whole vehicle. It has a considerable number of vehicle mathematical models built in, and these models have rich empirical parameters, so users can use them quickly, eliminating the complicated modeling and parameter adjustment process.

The CarSim model can run 10 times faster than real time on a computer. It can simulate the vehicle's response to driver control, 3D road surface and aerodynamic input. The simulation results are highly close to the real vehicle. It is mainly used to predict and simulate the vehicle's handling stability, braking, smoothness, power and economy. CarSim comes with a standard Matlab/Simulink interface, which can be easily co-simulated with Matlab/Simulink for the development of control algorithms. At the same time, a large amount of data results can be generated during the simulation for subsequent analysis or visualization using Matlab or Excel. CarSim also provides an RT version that can support mainstream HIL test systems, such as dSpace and NI systems, for easy joint HIL simulation.

VIRES VTD

VTD (Virtual Test Drive) is a complete modular simulation tool chain for ADAS, active safety and autonomous driving developed by VIRES of Germany. VIRES was acquired by MSC Software Group in 2017. VTD currently runs on the Linux platform. Its functions cover road environment modeling, traffic scenario modeling, weather and environment simulation, simple and physically realistic sensor simulation, scenario simulation management and high-precision real-time image rendering. It can support the full-cycle development process from SIL to HIL and VIL. The open modular framework can be easily simulated with third-party tools and plug-ins. VIRES is also the main contributor to the widely used autonomous driving simulation open formats OpenDrive, OpenCRG and OpenScenario. The functions and storage of VTD also rely on these open formats. The simulation process of VTD mainly consists of three steps: road network construction, dynamic scenario configuration, and simulation operation.

VTD provides a graphical interactive road network editor RoadNetwork Editor (ROD), which can simultaneously generate OpenDrive high-precision maps while using various traffic elements to build a complex road simulation environment with multiple types of lanes.

In the establishment of dynamic scenes, VTD provides a graphical interactive scenario editor ScenarioEditor, which provides traffic bodies with user-defined behavior control based on OpenDrive, or continuously running traffic flows in a certain area.

Whether it is SIL or HIL, whether it is real-time or non-real-time simulation, whether it is a stand-alone or high-performance computing environment, VTD provides corresponding solutions. When running, VTD can simulate real-time high-quality light and shadow effects, road reflections, vehicle body rendering, rain, snow and fog weather rendering, sensor imaging rendering, headlight visual effects, etc.

PTV Vissim

Vissim is a world-leading microscopic traffic flow simulation software provided by PTV of Germany. Vissim can easily build various complex traffic environments, including highways, large roundabouts, parking lots, etc., and can also simulate the interactive behaviors of motor vehicles, trucks, rail transit and pedestrians in one simulation scene. It is an effective tool for professional planning and evaluation of urban and suburban transportation facilities, and can also be used to simulate the impact of local emergency traffic and the evacuation of a large number of pedestrians.

Vissim's simulation can achieve high accuracy, including microscopic individual following and lane-changing behaviors, as well as group cooperation and conflict. Vissim has built-in multiple analysis methods, which can not only obtain a variety of specific data results under different circumstances, but also gain intuitive understanding from the high-quality 3D visualization engine. Autonomous driving algorithms can also be connected to Vissim to use simulated high-dynamic traffic environments for simulation testing.