SIMULATION PLATFORM FOR AUTONOMOUS DRIVING

VIRTUAL VEHICLE ENVIRONMENT

ZD Automotive and its partner develop various test tools for the validation of driver assistance systems, including mobile traffic information systems and automated driving prototypes as well as the simulation-based test tool GaiA.

When it comes to validation tools, the safety issues of the High-Level Automated Driving Systems (SAE Level 3-5, ADS) reveal more challenges than ADAS (SAE Level 1-2, Advanced Driver Assistance System). Unlike ADAS, the driver does not have to participate in the operation of high-level automated driving systems. According to the SAE, an ADS should be able to monitor the driving environment without a driver. This indicates higher requirements on the functional safety of the system as well as its validation.

To comply with these greater validation requirements, higher validation standards and a larger test case database is necessary. However, it increases the costs and bring up efficiency issues. To solve the challenges caused by ADS validation test and meet the requirements for its effectiveness and efficiency, the simulation-based test tool GaiA is an ideal solution.

GaiA can reproduce the road traffic as well as the vehicle in a virtual simulation environment to efficiently test whether the driving system can perform the expected tasks in different situations. This type of test system is the most important validation method for automated driving systems due to its low costs and ability to simulate large amounts of test drives.

FUNKTIONEN

In the user-friendly Interface, users can visualize any test scenarios in GaiA, which provides the following functions besides speed adjustment and data recording:

  • Generating Complex Scenarios Users can build roads from our road network database. Also, we provide a model library for construction of building which enables the generation of a complex scenario.
  • Dynamic Scenario Generation Module Thanks to the algorithms of the smart signal control system in GaiA, users can not only manually execute the traffic planning by themselves, but they also can test the vehicle in the intelligent traffic system.
  • 2D & 3D Graphics The graphics can be illustrated in 2D & 3D models according to different data. 3D models can be used for information such as raw data of long/short range radars. 2D is to illustrate the relations among simulation time, vehicle dynamic parameters and object sensing results.
  • Sensor Views With sensor views users can illustrate sensor data. The data can be exported as video file as well as json file for a lidar sensor.

FEATURES

  • Multidimensional Road Construction The simulation platform can be used to build roads sections of different widths, lengths, pitch/roll angles, curves and intersections. Coefficient of friction and road accessories like traffic lanes, bike lanes or sidewalks can be separately defined for each road segment. In addition, roadside objects in the model library can be added into the simulated scenario. The user can extend the library at any time. This module also supports the representation of captured scenarios.
  • Traffic Simulation Traffic participants (including bicycles and pedestrians) can be easily generated. Their motion status and behaviors can be set individually or by a standard automatic motion mode (AI Intelligent Traffic) that can cover most of the actual traffic conditions.
  • Vehicle Characteristics The vehicle has a realistic dynamic model. Perception sensor models can be added for numerous ranges of purposes (ACC sensors, automatic parking sensors, etc.) at different locations in the vehicle. The simulation efficiency can be ensured as well.
  • Automatic Test Control The system can load and run a set of test scenarios and record when a specific situation occurs. After the tests, it will also pass the information to the test report generator, which realizes unmanned automatic testing.
  • Weather Representation GaiA’s weather control module can change the weather during automatic testing to simulate weather conditions, such as fog, rain and snow. It can also show the influence of these weather conditions on perception sensors such as millimeter-wave radar and vehicle control.
  • Chart Drawing In the Graphics interface, GaiA can draw data from vehicles and sensors in real time, which makes it easier for test engineers to locate system issues more efficiently.
  • High-fidelity Extendable Tool Model Library GaiA can integrate tools and models from our huge simulation tool library, for example, vehicle dynamics two-track models, physical millimeter-wave radar models and physical lidar models. Based on the expansion, the simulation results will be more realistic, and the validation results will have a significant meaning to product development and validation
  • Interactive Automated Driving Simulation GaiA offers the possibility of interconnect simulations of multiple automated driving hosts in the same virtual scenario, enabling the tests of system-to-system interaction stability, reliability, and system functions based on interactive communications.