Research Report

Open Simulation Interface

A generic interface for the environment perception of automated driving functions in virtual scenarios.(Dated 03.02.2017)

T. Hanke, N. Hirsenkorn, C. van-Driesten, P. Garcia-Ramos, M. Schiementz, S. Schneider, E. Biebl

 

As the complexity of automated driving functions rapidly increases, the requirements for test and development methods are growing. Testing in virtual environments offers the advantage of completely controlled and reproducible environment conditions.

However, in order to achieve widespread use of driving simulators for function developers, the connection between the function development framework and the simulation environment has to rely on generic interfaces. To enable easy and straightforward compatibility between automated driving functions and the variety of driving simulation frameworks available, we propose the open simulation interface (OSI).

The open simulation interface contains an object based environment description using the message format of the protocol buffers library developed and maintained by Google [1]. OSI consists of two individual top level messages defining the GroundTruth interface and the SensorData interface.

The GroundTruth interface gives an exact view on the simulated objects in a global coordinate system. This message is populated using the data available internally and then published to external subscribers by a plugin running within the driving simulation framework.

The SensorData interface describes the objects in the reference frame of a sensor for environmental perception. It is generated from a GroundTruth message and can either be used to directly connect to an automated driving function using ideal simulated data, or may serve as input for a sensor model simulating limited perception as a replication of real world sensor behaviour.

A future research report is currently in preparation that contains the code of a run-time environment based on the Open Simulation Interface, including the conversions between GroudTruth and SensorData messages.

The authors’ vision is to be able to connect any automated driving function to any driving simulator with ease. This will simplify the integration and therefore significantly strengthen accessibility and usefulness of virtual testing.

If you are using or planning on using the Open Simulation Interface, please consider contacting the authors. This will enable further improvement of OSI. Moreover, take into account citing this research report in your scientific publications. Upon contacting the authors, we will add your publications and simulators that are using the Open Simulation Interface to the references.

 

Source Code 

 

Carlo van Driesten: Carlo.van-Driesten     @     bmw.de

Timo Hanke: Timo.Hanke     @    bmw.de

Nils Hirsenkorn: Nils.Hirsenkorn     @     tum.de

Pilar Garcia-Ramos: Pilar.Garcia-Ramos    @    bmw.de

Mark Schiementz: Mark.Schiementz    @    bmw.de  

Sebastian Schneider: Sebastian.SB.Schneider    @    bmw.de

Erwin Biebl: biebl    @    tum.de

References:

[1] developers.google.com/protocol-buffers/

Scientific publications and simulators supporting OSI:

T. Hanke, N. Hirsenkorn, B. Dehlink, A. Rauch, R. Rasshofer, and E. Biebl, “Generic architecture for simulation of ADAS sensors,” in International Radar Symposium, pp. 125–130, IEEE, 2015.

N. Hirsenkorn, T. Hanke, A. Rauch, B. Dehlink, R. Rasshofer, and E. Biebl, “A non-parametric approach for modeling sensor behavior,” in International Radar Symposium, pp. 131–136, DGON, 2015.

N. Hirsenkorn, T. Hanke, A. Rauch, B. Dehlink, R. Rasshofer, and E. Biebl, “Virtual sensor models for real-time applications,” Advances in Radio Science, vol. 14, pp. 31–37, 2016.

T. Hanke, N. Hirsenkorn, B. Dehlink, A. Rauch, R. Rasshofer, and E. Biebl, “Classification of Sensor Errors for the Statistical Simulation of Environmental Perception in Automated Driving Systems,” in International Conference on Intelligent Transportation Systems, IEEE, 2016.

N. Hirsenkorn, H. Kolsi, M. Selmi, A. Schaermann, T. Hanke, A. Rauch, R. Rasshofer, and E. Biebl, “Learning Sensor Models for Virtual Test and Development,” Workshop Fahrerassistenz und automatisiertes Fahren, vol. 11, 2017. 

N. Hirsenkorn, P. Subkowski, T. Hanke, A. Schaermann, A. Rauch, R. Rasshofer, and E. Biebl, “A Ray Launching Approach for Modeling an FMCW Radar System”, in International Radar Symposium, DGON, 2017, accepted.

A. Schaermann, A. Rauch, N. Hirsenkorn, T. Hanke, R. Rasshofer and E. Biebl, ”Validation of Virtual Perceptual Sensor Models,” in Intelligent Vehicles Symposium, IEEE, 2017, accepted.

T. Hanke, A. Schaermann, M. Geiger, K. Weiler, N. Hirsenkorn, S. Schneider and Erwin Biebl, ”Generation and Validation of Virtual Point Cloud Data for Automated Driving Systems,” in International Conference on Intelligent Transportation Systems, IEEE, 2017, submitted.