This content is not included in your SAE MOBILUS subscription, or you are not logged in.
A Simulation Tool for Virtual Validation and Verification of Advanced Driver Assistance Systems
ISSN: 0148-7191, e-ISSN: 2688-3627
Published April 06, 2021 by SAE International in United States
This content contains downloadable datasetsAnnotation ability available
Event: SAE WCX Digital Summit
Due to the infeasibility of exhaustive on-road testing of Automated Vehicles (AVs) and vehicles with Advanced Driver Assistance Systems (ADAS), virtual methods for verification and validation of such vehicles have gained prominence. In order to incorporate the variability in the characteristics of test scenarios such as surrounding traffic, weather, obstacles, road network, infrastructure features, etc., as well as provide the option of varying the fidelities of subsystem models, this study discusses a modular software block-set for virtual testing of AV/ADAS controllers based on open source tools. The core concept is to co-simulate the traffic, vehicle dynamics, sensors, and the 3D scenes required for perception. This is achieved using SUMO (Simulation of Urban MObility, a microscopic road-network-based traffic generation tool) and Unreal Engine (for 3D traffic flow generation). Due to the difference in the simulation timestep sizes of SUMO and Unreal Engine, as well as some of the subsystems such as vehicle sensors, such simulations pose a time-synchronization problem. Since SUMO also does not model detailed vehicle dynamics, a vehicle dynamics filter is utilized for multi-timestep simulation. In this paper, we present the architecture of the block-set, the uniqueness of which lies in its modularity in terms of mixing and matching various models for the subsystems involved. An example case using an existing environment in Unreal Engine is demonstrated. This block-set will allow the validation and verification of ADAS controls and perception algorithms in large numbers of scenarios as well as at edge cases which are particularly safety-critical. The simulations can be run in parallel, and specific test cases can also be visualized and individually analyzed.
CitationTulpule, P., Midlam-Mohler, S., Karumanchi, A., and Jin, Y., "A Simulation Tool for Virtual Validation and Verification of Advanced Driver Assistance Systems," SAE Technical Paper 2021-01-0865, 2021, https://doi.org/10.4271/2021-01-0865.
Data Sets - Support Documents
|Unnamed Dataset 1|
- Banerjee , S.S. , Jha , S. , Cyriac , J. , Kalbarczyk , Z.T. , and Iyer , R.K. Hands off the Wheel in Autonomous Vehicles?: A Systems Perspective on over a Million Miles of Field Data Proceedings - 48th Annual IEEE/IFIP International Conference on Dependable Systems and Networks, DSN 2018 Jul. 2018 586 597 10.1109/DSN.2018.00066
- Fraade-Blanar , L. , and Kalra , N. Autonomous Vehicles and Federal Safety Standards: An Exemption to the Rule Santa Monica, CA RAND Corporation 2017 https://www.rand.org/pubs/perspectives/PE258.html
- Dosovitskiy , A. , Ros , G. , Codevilla , F. , Lopez , A. , and Koltun , V. 2017 http://arxiv.org/abs/1711.03938
- Duy Son , T. , Bhave , A. , and Van Der Auweraer , H. Simulation-Based Testing Framework for Autonomous Driving Development Proceedings - 2019 IEEE International Conference on Mechatronics, ICM 2019 May 2019 576 583 10.1109/ICMECH.2019.8722847.
- Pilz , C. , Steinbauer , G. , Schratter , M. , and Watzenig , D. Nov. 2019 10.1109/ICCVE45908.2019.8964914
- Lopez , P.A. et al. Microscopic Traffic Simulation using SUMO IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC Dec. 2018, vol. 2018-Nov. 2575 2582 10.1109/ITSC.2018.8569938
- SUMO 2020 https://sumo.dlr.de/docs/Simulation/Traffic_Lights.html
- Rajamani , R. Vehicle Dynamics and Control Boston, MA Springer US 2012
- PolyPixel 2017 https://www.unrealengine.com/marketplace/en-US/product/downtown