We congratulate you on acceptance of your manuscript.
Abstract:
The rapid advancement of autonomous driving systems requires robust perception algorithms. Interpreting complex environments and simulation-based testing plays a vital role in validating these algorithms. This research explores the use of the Driving Scenario Designer app in MATLAB® workspace to perform high-fidelity sensor simulation, generate synthetic sensor data, and create dynamic virtual driving scenarios for testing perception systems. To emulate real-world driving conditions, the study focuses on designing scenarios involving multiple actors, including cars, pedestrians, cyclists, and barriers.
We construct and customize scenarios using the app with varying road layouts, traffic patterns, and environmental conditions. Sensor models such as radar, lidar, and cameras are simulated to produce synthetic data that mimics real sensor outputs. The scenarios are exported to the MATLAB® workspace for further analysis, enabling the evaluation of perception algorithms in detecting and tracking objects under different conditions.
Key contributions include a systematic methodology for scenario generation, sensor configuration, and data extraction, along with performance assessments of perception algorithms using synthetic datasets. The results demonstrate the effectiveness of the Driving Scenario Designer in accelerating algorithm development by providing a controlled yet flexible testing environment. This approach reduces reliance on costly physical prototypes while ensuring comprehensive validation across diverse driving conditions. The study highlights the app’s utility in autonomous vehicle research, offering a scalable solution for perception system verification.
References
MathWorks. (2023). Driving Scenario Designer User’s Guide.
Ulbrich, S., Menzel, T., Reschka, A., Schuldt, F., & Maurer, M. (2015). Defining and Substantiating the Terms Scene, Situation, and Scenario for Automated Driving. IEEE Intelligent Vehicles Symposium (IV).
Dosovitskiy, A., Ros, G., Codevilla, F., López, A., & Koltun, V. (2017). CARLA: An Open Urban Driving Simulator. Proceedings of the 1st Annual Conference on Robot Learning (CoRL).
Grigorescu, S., Trasnea, B., Cocias, T., & Macesanu, G. (2020). A Survey of Deep Learning Techniques for Autonomous Driving. Journal of Field Robotics, 37(3), 362-386.
Bansal, M., Krizhevsky, A., & Ogale, A. (2018). Chauffeurnet: Learning to Drive by Imitating the Best and Synthesizing the Worst. Robotics: Science and Systems (RSS).
Geiger, A., Lenz, P., & Urtasun, R. (2012). Are We Ready for Autonomous Driving? The KITTI Vision Benchmark Suite. IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
Rong, G., Shin, B. H., Tabatabaee, H., et al. (2020). LGSVL Simulator: A High Fidelity Simulator for Autonomous Driving. IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC).
Janai, J., Güney, F., Behl, A., & Geiger, A. (2020). Computer Vision for Autonomous Vehicles: Problems, Datasets, and State-of-the-Art. Foundations and Trends in Computer Graphics and Vision, 12(1-3), 1-308.
Kato, S., Tokunaga, S., Maruyama, Y., et al. (2018). Autoware on Board: Enabling Autonomous Vehicles with Embedded Systems. ACM/IEEE International Conference on Cyber-Physical Systems (ICCPS).
Pendleton, S. D., Andersen, H., Du, X., et al. (2017). Perception, Planning, Control, and Coordination for Autonomous Vehicles. Machines, 5(1), 6.
Chen, C., Seff, A., Kornhauser, A., & Xiao, J. (2015). DeepDriving: Learning Affordance for Direct Perception in Autonomous Driving. IEEE International Conference on Computer Vision (ICCV).
Li, Y., Ibanez-Guzman, J., & Ng, H. K. (2020). Lidar for Autonomous Driving: The Principles, Challenges, and Trends. IEEE Signal Processing Magazine, 37(4), 50-61.
Bojarski, M., Del Testa, D., Dworakowski, D., et al. (2016). End to End Learning for Self-Driving Cars. arXiv preprint arXiv:1604.07316.
Kong, J., Pfeiffer, M., Schildbach, G., & Borrelli, F. (2015). Kinematic and Dynamic Vehicle Models for Autonomous Driving Control Design. IEEE Intelligent Vehicles Symposium (IV).
NYCSEA