Abstract
Radars are widely used in automotive to deliver both interior and exterior environment sensing capability and enable functions such as cabin monitoring, automatic emergency breaking, adaptive cruise control etc. Complex verification of automotive radars is needed to ensure the safety of the final product. Validation is performed on many levels such as climate chambers tests, electromagnetic emission compliance, algorithm robustness and much more. Computer simulations are also widely used for this purpose. Automotive radars are modelled on several levels of abstraction starting from the physical wave propagation analysis to high level system output simulation. In the article a new approach to the detection level simulation of automotive radar is presented. It is based on the neural network system modelling. The performance verification based on publicly available nuScenes dataset is presented that allows to compare the results between different models.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Caesar, H., et al.: nuscenes: A multimodal dataset for autonomous driving. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11618–11628 (2020)
Dosovitskiy, A., Ros, G., Codevilla, F., Lopez, A. and Koltun, V.: CARLA: an open urban driving simulator. CoRR, abs/1711.03938 (2017)
Eder, T., Hachicha, R., Sellami, H., van Driesten, C., Biebl, E.: Data driven radar detection models: A comparison of artificial neural networks and non parametric density estimators on synthetically generated radar data. In: 2019 Kleinheubach Conference, pp. 1–4 (2019)
Markel, M., (Editor). In: Radar for Fully Autonomous Driving. Artech House (2022)
International Organization for Standardization: Road vehicles - safety of the intended functionality. Standard ISO/PAS 21448, 2019 (2019)
Hirsenkorn, N., Hanke, T., Rauch, A., Dehlink, B., Rasshofer, R., Biebl, E.: Virtual sensor models for real-time applications. Adv. Radio Sci. 14, 31–37 (2016)
Jasinski, M., Skruch, P., Komorkiewicz, M.: Validation framework for generic radar sensor models. IEEE Access 10, 18257–18267 (2022)
Kulkarni, C., Rajesh, M., Shylaja, S.S.: Dynamic binary cross entropy: An effective and quick method for model convergence. In: 2022 21st IEEE International Conference on Machine Learning and Applications (ICMLA), pp. 814–818 (2022)
Lelowicz, K., Jasiński, M., Piatek, M.: Generic sensor model for object detection algorithms validation. In: Andrzej Bartoszewicz, Jacek Kabziński, and Janusz Kacprzyk, editors, Advanced, Contemporary Control, pp. 1249–1260, Cham, 2020. Springer International Publishing
Magosi, Z.F., Li, H., Rosenberger, P., Wan, L., Eichberger, A.: A survey on modelling of automotive radar sensors for virtual test and validation of automated driving. Sensors 22(15), (2022)
Martowicz, A., Gallina, A., Karpiel, G.: Uncertainty propagation for vehicle detections in experimentally validated radar model for automotive application. In: 2019 24th International Conference on Methods and Models in Automation and Robotics (MMAR), pp. 606–611 (2019)
Muckenhuber, S., Museljic, E., Stettinger, G.: Performance evaluation of a state-of-the-art automotive radar and corresponding modeling approaches based on a large labeled dataset. J. Intell. Transport. Syst. 26(6), 655–674 (2022)
Nowak, M.K., Lelowicz, K.: Weight perturbation as a method for improving performance of deep neural networks. In: 2021 25th International Conference on Methods and Models in Automation and Robotics (MMAR), pp. 127–132 (2021)
Popov, A., et al.: and Nikolai Smolyanskiy. Real-time radar obstacle and free space detection for autonomous driving, Nvradarnet (2022)
Scheel, A., Dietmayer, K.: Tracking multiple vehicles using a variational radar model. IEEE Trans. Intell. Transport. Syst. 20(10), 3721-3736 (2017)
Suhre, A., Malik, W.: Simulating object lists using neural networks in automotive radar. In: 2018 19th International Conference on Thermal, Mechanical and Multi-Physics Simulation and Experiments in Microelectronics and Microsystems (EuroSimE), pp. 1–5 (2018)
Wheeler, T.A., Holder, M., Winner, H., Kochenderfer, M.J.: Deep stochastic radar models. In: 2017 IEEE Intelligent Vehicles Symposium (IV), pp. 47–53 (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Ciepiela, F., Nowak, M.K., Dworak, D., Komorkiewicz, M. (2023). Automotive Radar Detection Level Modeling with Neural Networks. In: Pawelczyk, M., Bismor, D., Ogonowski, S., Kacprzyk, J. (eds) Advanced, Contemporary Control. PCC 2023. Lecture Notes in Networks and Systems, vol 709. Springer, Cham. https://doi.org/10.1007/978-3-031-35173-0_25
Download citation
DOI: https://doi.org/10.1007/978-3-031-35173-0_25
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-35172-3
Online ISBN: 978-3-031-35173-0
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)