AI End-to-End Autonomous Driving
DOI:
https://doi.org/10.53469/wjimt.2025.08(01).08Keywords:
AI, End-to-End, Autonomous DrivingAbstract
This study aims to explore the performance and challenges of an end-to-end autonomous driving decision model based on a deep convolutional neural network (CNN) in practical applications. Firstly, this paper introduces the basic principles of deep convolutional neural networks and their application background in autonomous driving. Subsequently, it describes in detail the spatial feature extraction models based on deep convolutional networks, including the PilotNet baseline model and the spatial feature extraction model based on transfer learning. Based on this, an end-to-end decision model for longitudinal and lateral control of intelligent vehicles is constructed. The longitudinal and lateral control models are discussed separately, and more complex decision-making capabilities in autonomous driving scenarios are achieved through a combined model. Through experiments on the Udacity and Comma2k19 datasets, this paper demonstrates the performance of the end-to-end model. The experimental results show that the end-to-end model can effectively learn driving strategies from image data and exhibits good generalization ability and robustness under different environmental conditions. Feature visualization analysis further reveals the internal mechanism and decision basis of the model. Although the end-to-end model shows great potential in autonomous driving, this study also reveals some challenges in its practical application, including the interpretability of the model, the quality and diversity of the dataset, and the decision-making ability in complex environments. Future research should focus on addressing these issues to promote the further development and application of autonomous driving technology. Overall, this study provides a comprehensive research framework and practical foundation for end-to-end autonomous driving decision models based on deep learning.
References
Kong Huifang, Liu Runwu, Hu Jie. End-to-End Autonomous Driving Model Based on Multimodal Intermediate Representation [J]. Modern Manufacturing Engineering, 2024, (03):70-78.
Liu Y, Wang Y, Li Q. Lane detection based on real-time semantic segmentation for end-to-end autonomous driving under low-light conditions [J]. Digital Signal Processing, 2024, 155:104752.
Wang Liyong, Xie Min, Su Qinghua, et al. Research on End-to-End Autonomous Driving Model for Temporary Roads [J]. Journal of Chongqing University of Technology (Natural Science), 2024, 38(09):48-54.
Ideal Auto to Fully Push No Map NOA Release End-to-End + VLM New Autonomous Driving Technology Architecture in July [J]. World Automobile, 2024, (08):72-75.
Jiang W, Wang L, Zhang T, et al. RobustE2E: Exploring the Robustness of End-to-End Autonomous Driving [J]. Electronics, 2024, 13(16):3299-3299.
Hu Shuanglu, Hua Xianping, Dou Min, et al. Current Status and Development Trends of Automotive End-to-End Autonomous Driving [J]. Times Auto, 2024, (13):4-6+109.
Wu Wufei, Li Wenbo, Bai Di, et al. Design of an End-to-End Autonomous Driving Method with Spatiotemporal Feature Fusion [J]. Journal of Nanchang University (Engineering Edition), 2024, 46(02):162-169.
Yiming Pan, et al. “Application of Three-Dimensional Coding Network in Screening and Diagnosis of Cervical Precancerous Lesions.” Frontiers in Computing and Intelligent Systems, vol. 6, no. 3, 2023, pp. 61–64, https://doi.org/10.54097/mi3VM0yB.
Zhixing Company collaborates with Tsinghua University and others to complete the domestic first set of end-to-end autonomous driving system open road testing [J]. Smart Building and Smart City, 2024, (05):4.
Sifang Lin, et al. “Artificial Intelligence and Electroencephalogram Analysis: Innovative Methods for Optimizing Anesthesia Depth.” Journal of Theory and Practice in Engineering and Technology, vol. 1, no. 4, Dec. 2024, pp. 1–10, https://doi.org/10.5281/zenodo.14457933.
Miao Tian, et al. “The Application of Artificial Intelligence in Medical Diagnostics: A New Frontier.” Academic Journal of Science and Technology, vol. 8, no. 2, Dec. 2023, pp. 57–61, https://doi.org/10.54097/ajst.v8i2.14945.
Lü Yanzhi, Wei Chao, He Yuanhao. End-to-End Autonomous Lane Change Method Based on GCN and CIL [J]. Automotive Engineering, 2023, 45(12):2310-2317.
Li Shengbo, Liu Chang, Yin Yuming, et al. Key Technologies and Development Trends of End-to-End Autonomous Driving Systems [J]. Artificial Intelligence, 2023, (05):1-16. DOI:10.16453/j.2096-5036.202350.
Zhenbo H, Shiliang S, Jing Z, et al. Multi-modal policy fusion for end-to-end autonomous driving [J]. Information Fusion, 2023, 98.
Yuxiang Liu, et al. “Grasp and Inspection of Mechanical Parts Based on Visual Image Recognition Technology.” Journal of Theory and Practice of Engineering Science, vol. 3, no. 12, Dec. 2023, pp. 22–28, https://doi.org/10.53469/jtpes.2023.03(12).04.
Zhu Bo, Zhang Jiwei, Tan Dongkui, et al. End-to-End Autonomous Driving Method Based on Multi-source Sensors and Navigation Maps [J]. Journal of Automotive Safety and Energy, 2022, 13(04):738-749.
Jie H, Huifang K, Qian Z, et al. Enhancing Scene Understanding Based on Deep Learning for End-to-End Autonomous Driving [J]. Engineering Applications of Artificial Intelligence, 2022, 116.
Lü Yisheng, Liu Yahui, Chen Yuanyuan, et al. Predicting Steering Angles of End-to-End Autonomous Vehicles by Fusing Spatiotemporal Features [J]. Journal of Highway and Transportation Research and Development, 2022, 35(03):263-272.
Shiwei Cheng, et al. “3D Pop-Ups: Omnidirectional Image Visual Saliency Prediction Based on Crowdsourced Eye-Tracking Data in VR.” Displays, vol. 83, July 2024, p. 102746, Elsevier, https://doi.org/10.1016/j.displa.2024.102746.
Lu Xiao, Zhu Yiwei, Yang Muhua, et al. Reinforcement Learning End-to-End Autonomous Driving Decision Method Uniting Image and Monocular Depth Features [J]. Journal of Wuhan University (Information Science Edition), 2021, 46(12):1862-1871.
Chu Duanfeng, Wang Rukang, Wang Jingyi, et al. Research Progress and Challenges in End-to-End Autonomous Driving [J/OL]. Journal of Highway and Transportation Research and Development, 1-29 [2024-10-25].
Yang Lu, Wang Yiquan, Liu Jiaqi, et al. End-to-End Behavior Decision Method for Autonomous Driving Based on Dual Delayed Deep Deterministic Policy Gradient Algorithm with Discrete Action Fusion [J]. Traffic Information and Safety, 2022, 40(01):144-152.
Heyao Chen, et al. “Threat Detection Driven by Artificial Intelligence: Enhancing Cybersecurity with Machine Learning Algorithms.” Cybersecurity Innovations Conference, Nov. 2024, p. 45, https://doi.org/10.53469/wjimt.2024.07(06).09.
Kuo Wei, et al. “Strategic Application of AI Intelligent Algorithm in Network Threat Detection and Defense.” Journal of Theory and Practice of Engineering Science, vol. 4, no. 01, Jan. 2024, pp. 49–57, https://doi.org/10.53469/jtpes.2024.04(01).07.
Zhou Xinyang, Song Zhenbo, Li Weiqing, et al. End-to-End Autonomous Driving Based on LSTM Deep Reinforcement Learning [J]. Computer Simulation, 2024, 41(02):172-178.
Gao Chi. Can "End-to-End" Disrupt Autonomous Driving? [J]. Auto and Parts, 2024, (11):58-59.
Wangmei Chen, et al. “Applying Machine Learning Algorithm to Optimize Personalized Education Recommendation System.” Journal of Theory and Practice of Engineering Science, vol. 4, no. 01, Feb. 2024, pp. 101–108, https://doi.org/10.53469/jtpes.2024.04(01).14.
Lai Chenguang, Yang Xiaoqing, Hu Bo, et al. End-to-End Autonomous Driving Strategy Based on Deep Deterministic Policy Gradient Algorithm [J]. Journal of Chongqing University of Technology (Natural Science), 2023, 37(01):56-65.