The Current Development and Future Prospects of Autonomous Driving Driven by Artificial Intelligence
Main Article Content
Keywords
autonomous driving, artificial intelligence, multimodal perception, reinforcement learning, intelligent transportation system
Abstract
This paper explores the application and development of artificial intelligence in autonomous driving and analyses its current status, challenges, and future trends. Autonomous driving systems integrate multiple core technologies in vehicle perception and driving decision-making, achieving a leap from assisted driving to commercial deployment. Leveraging emerging methods such as machine learning, deep learning, and reinforcement learning, autonomous driving systems have significantly improved perception accuracy, decision-making capabilities, and environmental adaptability. However, current autonomous driving systems still face technical bottlenecks, including insufficient model generalizability and low training efficiency, while also encountering legal and societal challenges such as data privacy protection, accident liability determination, and algorithmic ethical biases. In the future, high-precision multimodal perception architectures, edge computing deployment solutions, and the construction of a vehicle‒road collaborative ecosystem will be key breakthrough directions for enabling fully autonomous driving across all scenarios.
References
- Coelho, D., Oliveira, M., & Santos, V. (2024). RLfOLD: Reinforcement learning from online demonstrations in urban autonomous driving. Proceedings of the AAAI Conference on Artificial Intelligence, 38(10), 11660-11668. https://doi.org/10.1609/AAAI.V38I10.29049
- Hu, X., Chen, P., Wen, Y., Tang, B., & Chen, L. (2024). Long and short-term constraints driven safe reinforcement learning for autonomous driving. arXiv preprint, arXiv:2403.18209. https://doi.org/10.48550/arXiv.2403.18209
- Jiang, X., Hou, Y., Tian, H., & Zhu, L. (2024). Mirror complementary transformer network for RGB-thermal salient object detection. IET Computer Vision, 18(1), 15-32. https://doi.org/10.1049/cvi2.12221
- Madake, J., Lokhande, T., Mali, A., Mahale, N., & Bhatlawande, S. (2024, 8-9 May 2024). TransVOD: Transformer-based visual object detection for self-driving cars [Paper presentation]. 2024 International Conference on Current Trends in Advanced Computing (ICCTAC), Bengaluru, India.
- Pham, L. H., Tran, D. N. N., & Jeon, J. W. (2020, 1-3 Nov. 2020). Low-light image enhancement for autonomous driving systems using DriveRetinex-Net [Paper presentation]. 2020 IEEE International Conference on Consumer Electronics - Asia (ICCE-Asia), Seoul, Korea.
- Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł., & Polosukhin, I. (2017). Attention is all you need [Paper presentation]. 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA.
- Wu, J., Huang, Z., & Lv, C. (2023). Uncertainty-aware model-based reinforcement learning: Methodology and application in autonomous driving. IEEE Transactions on Intelligent Vehicles, 8(1), 194-203. https://doi.org/10.1109/TIV.2022.3185159
- Xu, X., Zhang, T., Yang, J., Johnson-Roberson, M., & Huang, X. (2024). Self-supervised pre-training for transferable multi-modal perception. arXiv e-prints, arXiv: 2405.17942. https://doi.org/10.48550/arXiv.2405.17942
Article Sidebar
This work is licensed under a Creative Commons Attribution 4.0 International License.