Abstract
Intelligent Driver Assistance Services (IDAS) strongly emphasize leveraging artificial intelligence (AI) technology to enhance driver assistance systems’ capabilities, enabling drivers to operate their vehicles more safely and comfortably. Despite significant advancements in Advanced Driving Assistance Systems (ADAS) over the past decade, efficiently providing personalized decision-making for all kinds of drivers is still a far-reaching challenge. This paper proposes a novel framework for rapidly configuring and training context-aware personalized intelligent driver assistance services. Based on the cloud-edge collaboration, we investigate the efficient generation and updating of personalized decision models on the edge and the effective integration of personalized experiences in the cloud, forming a complete closed loop of driving experience accumulation. In addition, a method for configuring the driving environment perception model is proposed, considering the variations in different edge environments and edge equipment. This ensures the contextual relevance of the personalized decision-making model and enhances its effectiveness. The proposed approach is evaluated in CARLA, an open urban driving simulator. The results demonstrate that our approach surpasses other methods regarding training time, communication cost, and convergence.
This work is supported in part by National Nature Science Foundation of China under Grant No. U1908212 and Liaoning Scientific And Technological Project No. 1653137155953.
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
Similar content being viewed by others
References
Cao, D., et al.: Future directions of intelligent vehicles: potentials, possibilities, and perspectives. IEEE Trans. Intell. Veh. 7(1), 7–10 (2022). https://doi.org/10.1109/TIV.2022.3157049
Choudhary, T., Mishra, V., Goswami, A., Sarangapani, J.: A comprehensive survey on model compression and acceleration. Artif. Intell. Rev. 53(7), 5113–5155 (2020)
Deng, Q., Söffker, D.: A review of hmm-based approaches of driving behaviors recognition and prediction. IEEE Trans. Intell. Veh. 7(1), 21–31 (2021)
Dosovitskiy, A., Ros, G., Codevilla, F., Lopez, A., Koltun, V.: Carla: an open urban driving simulator. In: Conference on Robot Learning, pp. 1–16. PMLR (2017)
Hahn, S.J., Jeong, M., Lee, J.: Connecting low-loss subspace for personalized federated learning. In: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pp. 505–515 (2022)
Huang, W., Braghin, F., Arrigoni, S.: Autonomous vehicle driving via deep deterministic policy gradient. In: International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, vol. 59216, p. V003T01A017. American Society of Mechanical Engineers (2019)
Kiran, B.R., et al.: Deep reinforcement learning for autonomous driving: a survey. IEEE Trans. Intell. Transp. Syst. 23(6), 4909–4926 (2021)
Li, Y.: Deep reinforcement learning: an overview. arXiv preprint arXiv:1701.07274 (2017)
Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971 (2015)
Liu, J., et al.: From distributed machine learning to federated learning: a survey. Knowl. Inf. Syst. 64(4), 885–917 (2022)
Min, K., Kim, H., Huh, K.: Deep distributional reinforcement learning based high-level driving policy determination. IEEE Trans. Intell. Veh. 4(3), 416–424 (2019)
Nidamanuri, J., Nibhanupudi, C., Assfalg, R., Venkataraman, H.: A progressive review: emerging technologies for ADAS driven solutions. IEEE Trans. Intell. Veh. 7(2), 326–341 (2021)
Ren, W.Q., et al.: A survey on collaborative DNN inference for edge intelligence. Mach. Intell. Res. 1–25 (2023)
Tan, A.Z., Yu, H., Cui, L., Yang, Q.: Towards personalized federated learning. IEEE Trans. Neural Netw. Learn. Syst. (2022)
Wu, Y., Tan, H., Ran, B.: Differential variable speed limits control for freeway recurrent bottlenecks via deep reinforcement learning. arXiv preprint arXiv:1810.10952 (2018)
Xu, D., He, X., Su, T., Wang, Z.: A survey on deep neural network partition over cloud, edge and end devices. arXiv preprint arXiv:2304.10020 (2023)
Xu, X., Li, H., Xu, W., Liu, Z., Yao, L., Dai, F.: Artificial intelligence for edge service optimization in internet of vehicles: a survey. Tsinghua Sci. Technol. 27(2), 270–287 (2021)
Ye, Y., Zhang, X., Sun, J.: Automated vehicle’s behavior decision making using deep reinforcement learning and high-fidelity simulation environment. Transp. Res. Part C Emerg. Technol. 107, 155–170 (2019)
Zhang, J., et al.: Fedala: adaptive local aggregation for personalized federated learning. arXiv preprint arXiv:2212.01197 (2022)
Zhuo, H.H., Feng, W., Lin, Y., Xu, Q., Yang, Q.: Federated deep reinforcement learning. arXiv preprint arXiv:1901.08277 (2019)
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
Na, J., Zhang, H., Zhu, O., Xie, W., Zhang, B., Zhang, C. (2023). Fast Configuring and Training for Providing Context-Aware Personalized Intelligent Driver Assistance Services. In: Monti, F., Rinderle-Ma, S., Ruiz Cortés, A., Zheng, Z., Mecella, M. (eds) Service-Oriented Computing. ICSOC 2023. Lecture Notes in Computer Science, vol 14420. Springer, Cham. https://doi.org/10.1007/978-3-031-48424-7_16
Download citation
DOI: https://doi.org/10.1007/978-3-031-48424-7_16
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-48423-0
Online ISBN: 978-3-031-48424-7
eBook Packages: Computer ScienceComputer Science (R0)