8 autonomous vehicle simulation software

Autonomous vehicle simulation software meets the needs of algorithm testing and avoids safety hazards caused by road testing.

Self-driving cars rely heavily on simulation software for testing due to cost, time, and regulatory constraints in road testing.
8 prominent autonomous vehicle simulation software solutions involved in this blog are CarSim, Carmaker, PreScan, PTV Vissim, SUMO, VIRES VTD, rFpro, and Cognata, each offering unique features and capabilities.
These software solutions enable comprehensive testing of autonomous driving algorithms, vehicle dynamics, traffic scenarios, and sensor interactions, crucial for the safe and efficient deployment of autonomous vehicles.

Self-driving cars require extensive road testing before commercial deployment. However, this process is costly and time-consuming, and open road tests face regulatory restrictions and safety risks. Consequently, the industry widely adopts autonomous driving simulation testing, which accounts for around 90% of algorithm testing. This blog introduces 8 existing automatic driving simulation software solutions.

1. CarSim

CarSim, and the related TruckSim and BikeSim, are powerful dynamics simulation software developed by Mechanical Simulation, Inc. and are widely used by OEMs and suppliers around the world.

The CarSim model can be run on a computer 10 times faster than real-time, and can simulate the vehicle’s response to driver control, 3D road surface and aerodynamic inputs, with the simulation, results highly approximating those of a real vehicle and is mainly used for predicting and simulating the vehicle’s handling stability, braking, smoothness, dynamics, and economy.CarSim comes with standard Matlab/Simulink interfaces, which can be easily used to simulate the vehicle’s driving dynamics and the driver’s response. CarSim comes with a standard Matlab/Simulink interface, which makes it easy to co-simulate with Matlab/Simulink for control algorithm development, and at the same time, it can generate a large amount of data results for subsequent analysis or visualisation using Matlab or Excel. DSpace and NI’s system to facilitate joint HIL simulation.

Also read: Autonomous vehicles: 3 potential drawbacks

2. Carmaker

Carmaker, and the related TruckMaker and MotorcycleMaker, are dynamics, ADAS and autonomous driving simulation software from IPG, Germany. Carmaker is first and foremost an excellent dynamics simulation software, providing accurate vehicle body models (engine, chassis, suspension, transmission, steering, etc.), in addition to this, Carmaker also creates closed-loop simulation systems that include the vehicle, driver, road, and traffic environment. Carmaker also creates a closed-loop simulation system including vehicle, driver, road and traffic environment.

As a platform software, CarMaker can be integrated with many third-party software, such as ADAMS, AVLCruise, rFpro, etc., to take advantage of the strengths of each software for joint simulation. Meanwhile, CarMaker’s supporting hardware provides a large number of board interfaces, which can be conveniently used for HIL testing with ECUs or sensors.

Also read: 7 autonomous driving conferences to explore the future of mobility

3. PreScan

PreScan is an ADAS test simulation software developed by TassInternational and acquired by Siemens in August 2017.PreScan is a simulation platform consisting of a GUI-based, pre-processor for defining scenarios and a runtime environment for executing them. The main interfaces used by engineers to create and test algorithms include MATLAB and Simulink.PreScan can be used for applications ranging from model-based controller design (MIL) to real-time testing using software-in-the-loop (SIL) and hardware-in-the-loop (HIL) systems.

PreScan can operate in open-loop and closed-loop as well as offline and online modes. It is an open software platform with a flexible interface to third-party vehicle dynamics models (e.g. CarSIM and dSPACEASM) and third-party HIL simulators/hardware (e.g. ETAS, dSPACE, and Vector).

4. PTV Vissim

Vissim is the world’s leading microscopic traffic flow simulation software provided by PTV, Germany. vissim can easily build a variety of complex traffic environments, including motorways, large roundabouts, car parks, etc., and can also be used to simulate the interactions of motor vehicles, trucks, rail traffic and pedestrians in a single simulation scenario. It is an effective tool for professional planning and evaluation of urban and suburban transport facilities, and can also be used to simulate the impact of local emergency traffic, the evacuation of large numbers of pedestrians.

Vissim’s simulations can achieve a high degree of accuracy, including microscopic individual following and lane changing behaviour, as well as group cooperation and conflict.Vissim has a wide range of built-in analytical tools, both for obtaining a wide range of specific data results for different scenarios, as well as for gaining intuitive understanding from the high-quality 3D visualisation engine. Driverless algorithms can also be simulated and tested using simulated highly dynamic traffic environments by accessing Vissim.

5. SUMO

SUMO is an open source microscopic continuous traffic flow simulation software developed by the German National Aerospace Centre. It comes with a traffic simulation network editor that allows you to interactively add roads, edit lane connections, process intersection zones, edit signal timings, etc. Road networks from Vissim, OpenStreetMap, OpenDrive can also be converted by a separate conversion programme. Routes for each vehicle can be specified by editing a routing file, or randomly generated using parameters. At runtime, it can simultaneously handle several square kilometres and up to tens of thousands of vehicles for continuous traffic simulation needs, and also provides an OpenGL-based visualisation side to display the results of traffic simulation in real time.

6. VIRES VTD

VTD (Virtual Test Drive) is a complete modular simulation toolchain for ADAS, active safety and autonomous driving developed by VIRES, Germany.VIRES has been acquired by the MSC Software Group in 2017.VTD currently runs on the Linux platform, and its functionality covers road environment modelling, traffic scene modelling, weather and environment simulation, simple and physically realistic sensor simulation, scenario simulation management, and high-precision real-time screen rendering. VIRES supports full-cycle development processes from SIL to HIL and VIL, and its open modular framework allows for easy co-simulation with third-party tools and plug-ins.VIRES is also a major contributor to the widely-used open formats for automated driving simulation, OpenDrive, OpenCRG, and OpenScenario, and VTD’s functionality and storage are also based on these open formats. The simulation process of VTD mainly consists of three steps: road network construction, dynamic scenario configuration, and simulation operation.

7. rFpro

rFpro is a British company founded in 2008 and started as a track reconstruction and simulation project within an F1 team, which dictated the high speed, real-time and accuracy requirements of the simulation from the outset. rFpro uses high-precision phase-method LIDAR to scan the data pavement and shoulder, which generates a highly accurate digital model of the road surface with a resolution of 1cm, as well as a TOF LIDAR to scan roadside streets and scenes. At the same time, rFPro uses TOF LIDAR to scan the streets and scenes on the side of the road. rFpro can provide virtual scenes for dynamics simulation, ADAS, and automated driving tests that are highly compatible with the real environment. rFpro has created high-precision virtual scenes for many race tracks and test scenarios using this method, including F1, NASCAR, and IndyCar.

8. Cognata

Cognata is an Israeli-based self-driving simulation startup founded in 2016 that closed an $18.5 million Series B funding round in late 2018. Cognata uses a combination of artificial intelligence, deep learning, and computer vision to recreate cities on its 3D simulation platform to provide customers with a variety of test scenarios that mimic real-world test driving.

Cognata’s technology is divided into three main areas. For static environments, Cognata’s TrueLife3DMesh engine uses computer vision and deep learning algorithms to automatically generate virtual simulation environments including buildings, roads, lane markings, and traffic signs based on maps and satellite images. For dynamic simulation, Cognata builds accurate and scalable traffic simulation models and weather and lighting models based on historical street traffic data, simulating a wide range of vehicles and pedestrians in real-world environments. The entire virtual simulation engine combines static and dynamic simulation models to simulate the interaction of sensors with changes in the simulated environment, providing a complete feedback loop for the autonomous driving system to be tested.