SceGAN: A method for generating autonomous vehicle cut-in scenarios on highways based on deep learning
), Abstract
With the increasing level of automation of autonomous vehicles, it is important to conduct comprehensive and extensive testing before releasing autonomous vehicles into the market. Traditional public road and closed-field testing failed to meet the requirements of high testing efficiency and scenario coverage. Therefore, scenario-based autonomous vehicle simulation testing has emerged. Many scenarios form the basis of simulation testing. Generating additional scenarios from an existing scenario library is a significant problem. Taking the scenarios of a proceeding vehicle cutting into an adjacent lane on highways as an example, based on an autoencoder and a generative adversarial network (GAN), a method that combines Transformer to capture the features of a long-time series, called SceGAN, is proposed to model and generate scenarios of autonomous vehicles on highways. An evaluation system is established to analyze the reliability of SceGAN using discriminative and predictive scores and further evaluate the effect of scenario generation in terms of similarity and coverage. Experiments showed that compared with TimeGAN and AEGAN, SceGAN is superior in data fidelity and availability, and their similarity increased by 27.22% and 21.39%, respectively. The coverage increased from 79.84% to 93.98% as generated scenarios increased from 2,547 to 50,000, indicating that the proposed method has a strong generalization capability for generating multiple trajectories, providing a basis for generating test scenarios and promoting autonomous vehicle testing.
Keywords
References
Barz, B., Rodner, E., Garcia, Y. G., Denzler, J., 2019. Detecting regions of maximal divergence for spatio-temporal anomaly detection. IEEE Trans Pattern Anal Mach Intell, 41, 1088–1101.
Demetriou, A., Alfsvåg, H., Rahrovani, S., Haghir Chehreghani, M., 2023. A deep learning framework for generation and analysis of driving scenario trajectories. SN Comput Sci, 4, 1–14.
Duan, J., Gao, F., He, Y., 2022. Test scenario generation and optimization technology for intelligent driving systems. IEEE Intell Transport Syst Mag, 14, 115–127.
Essa, M., Sayed, T., 2019. Full Bayesian conflict-based models for real time safety evaluation of signalized intersections. Accid Anal Prev, 129, 367–381.
Feng, S., Feng, Y., Sun, H., Bao, S., Zhang, Y., Liu, H. X., 2021. Testing scenario library generation for connected and automated vehicles, part II: Case studies. IEEE Trans Intell Transport Syst, 22, 5635–5647.
Feng, S., Sun, H., Yan, X., Zhu, H., Zou, Z., Shen, S. et al., 2023. Dense reinforcement learning for safety validation of autonomous vehicles. Nature, 615, 620–627.
Feng, T., Liu, L., Xing, X., Chen, J., 2022. Multimodal critical-scenarios search method for test of autonomous vehicles. J Intell Connect Veh, 5, 167–176.
Hochreiter, S., Schmidhuber, J., 1997. Long short-term memory. Neural Comput, 9, 1735–1780.
Li, Y., Tao, J., Wotawa, F., 2020. Ontology-based test generation for automated and autonomous driving functions. Inf Softw Technol, 117, 106200.
Lin, H., Liu, Y., Li, S., Qu, X., 2023. How generative adversarial networks promote the development of intelligent transportation systems: A survey. IEEE/CAA J Autom Sinica, 10, 1781–1796.
Liu, R. W., Guo, Y., Lu, Y., Chui, K. T., Gupta, B. B., 2022a. Deep network-enabled haze visibility enhancement for visual IoT-driven intelligent transportation systems. IEEE Trans Ind Inf, 19, 1581–1591.
Liu, Y., Wu, F., Lyu, C., Li, S., Ye, J., Qu, X., 2022b. Deep dispatching: A deep reinforcement learning approach for vehicle dispatching on online ride-hailing platform. Transp Res Part E Logist Transp Rev, 161, 102694.
Maaten, L.V., Hinton, G.E., 2008. Visualizing Data using t-SNE. J Mach Learn Res, 9, 2579–2605.
Xu, Y., Zou, Y., Sun, J., 2018. Accelerated testing for automated vehicles safety evaluation in cut-in scenarios based on importance sampling, genetic algorithm and simulation applications. J Intell Connect Veh, 1, 28–38.
Zhou, W.S., Zhu, Y., Zhao, X.M., Wang, R.M., Xu, Z.G., 2021. Vehicle cut-in test case generation methods for testing of autonomous driving on highway. Automob Technol, 1, 11–18.
Zong, F., Wang, M., Tang, J., Zeng, M., 2022a. Modeling AVs & RVs’ car-following behavior by considering impacts of multiple surrounding vehicles and driving characteristics. Phys A Stat Mech Appl, 589, 126625.
Zong, F., He, Z., Zeng, M., Liu, Y., 2022b. Dynamic lane changing trajectory planning for CAV: A multi-agent model with path preplanning. Transp B Transp Dyn, 10, 266–292.
京公网安备11010802044758号