A Study of Road Tracking Immunity for Autonomous Driving
Article Sidebar
Main Article Content
Abstract
With the advancement of deep learning research, autonomous driving technology has become increasingly mature. However, the accompanying issue is that environmental interference may pose safety hazards for autonomous driving, presenting a significant threat. Therefore, this paper aims to evaluate the resilience of autonomous vehicles to environmental interference by studying the fundamental road-tracking task of autonomous driving. Following the model of real autonomous driving vehicles, we constructed a 1:20-scale intelligent model car, Jetracer, and used it to simulate the road-tracking task of autonomous driving. We designed four different environments, first collecting varying numbers of image data in the original environment for comparative analysis. Then, we selected ResNet18 and ResNet34 as models for training and loaded them onto Jetracer for testing in the four different environments. The experimental results indicate that as the number of images in the dataset increases, the effectiveness of road tracking also gradually improves. Meanwhile, we found that ResNet18 is more suitable as a training model compared to ResNet34. Additionally, Jetracer demonstrates a certain degree of interference resistance, where slight or localized environmental changes do not significantly affect its road tracking performance. However, if there are significant overall environmental changes or new environments are introduced, Jetracer’s road-tracking performance is severely impacted.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
เนื้อหาข้อมูล
References
J. Qu, “Multi-task in autonomous driving through RDNet18-CA with LiSHTL-S loss function,” ECTI Trans. Comput. Inf. Technol., vol. 18, no. 2, pp. 158-173, Apr. 2024.
S. Ding and J. Qu, “Research on multi-tasking smart cars based on autonomous driving systems,” SN Comput. Sci., vol. 4, no. 3, p. 292, Mar. 2023.
K. Tsiakas, I. Kostavelis, D. Giakoumis, and D. Tzovaras, “Road tracking in semi-structured environments using spatial distribution of LiDAR data,” in Artificial Intelligence Applications and Innovations, Cham, Switzerland: Springer, 2021, ch. 32, pp. 432-445.
A. Kumar, T. Saini, P. B. Pandey, and A. Agarwal, “Vision-based outdoor navigation of self-driving car using lane detection,” Int. J. Inf. Technol., vol. 14, no. 1, pp. 215-227, Aug. 2022.
Y. Li and J. Qu, “Intelligent road tracking and real-time acceleration-deceleration for autonomous driving using modified convolutional neural networks,” Curr. Appl. Sci. Technol., vol. 22, no. 6, pp. 1-26, Mar. 2022.
Q. Zhang, T. Du, and C. Tian, “Self-driving scale car trained by deep reinforcement learning,” arXiv, 2019. [Online]. Available: https://arxiv.org/abs/1909.03467 [Accessed: Aug. 15, 2025].
B. Peng et al., “End-to-end omous driving through dueling double deep Q-network,” Automot. Innov., vol. 4, pp. 328-337, Jun. 2021.
S. Yuenyong and Q. Jian, “Generating synthetic training images for deep reinforcement learning of a mobile robot,” J. Intell. Inform. Smart Technol., vol. 2, no. 3, pp. 16-20, 2017.
X. Du, M. H. Ang, and D. Rus, “Car detection for autonomous vehicle: LiDAR and vision fusion approach through deep learning framework,” in Proc. IEEE/RSJ Int. Conf. Intell. Robots Syst. (IROS), Sep. 2017, pp. 749-754.
U. Karni, S. S. Ramachandran, K. Sivaraman, and A. K. Veeragaghaven, “Development of autonomous downscaled model car using neural networks and machine learning,” in Proc. Int. Conf. Comput. Methodol. Commun. (ICCMC), 2019, pp. 1089-1094.
Y. Bae et al., “Prototyping a system of cost-effective autonomous guided vehicles,” in Proc. Annu. Gen. Donald R. Keith Memorial Conf., 2021, pp. 138-143.
K. L. Lee and H. Y. Lam, “Development of deep learning autonomous car using Raspberry Pi,” Prog. Eng. Appl. Technol., vol. 2, no. 1, pp. 534-548, Jun. 2021.
S. Zang et al., “The impact of adverse weather conditions on autonomous vehicles: How rain, snow, fog, and hail affect the performance of a self-driving car,” IEEE Veh. Technol. Mag., vol. 14, no. 2, pp. 103-111, Mar. 2019.
S. Valladares et al., “Design and implementation of an autonomous vehicle prototype,” in Proc. 4th Int. Conf. Intell. Human Syst. Integr. (IHSI), 2021, pp. 343-349.
V. Rausch et al., “Learning a deep neural net policy for end-to-end control of autonomous vehicles,” in Proc. Am. Control Conf. (ACC), 2017, pp. 4914-4919.
Z. Chen and X. Huang, “End-to-end learning for lane keeping of self-driving cars,” in Proc. IEEE Intell. Vehicles Symp. (IV), 2017, pp. 1856-1860.
C. J. Willmott and K. Matsuura, “Advantages of the Mean Absolute Error (MAE) over the Root Mean Square Error (RMSE) in assessing average model performance,” Clim. Res., vol. 30, no. 1, pp. 79-82, 2005.
W. -Y. Lin, W. -H. Hsu, and Y. -Y. Chiang, “A combination of feedback control and vision-based deep learning mechanism for guiding self-driving cars,” in Proc. IEEE Int. Conf. Artif. Intell. Virtual Reality (AIVR), 2018, pp. 262-266.
M. G. Bechtel et al., “Deeppicar: A low-cost deep neural network-based autonomous car,” in Proc. IEEE Int. Conf. Embedded Real-Time Comput. Syst. Appl.(RTCSA), 2018, pp. 11-21.
T. -D. Do et al., “Real-time self-driving car navigation using deep neural network,” in Proc. Int. Conf. Green Technol. Sustain. Dev. (GTSD), 2018, pp. 7-12.
Z. Nie and J. Qu, “Multi-task autonomous driving based on improved convolutional neural network and ST loss in MTS and MOD modes,” Curr. Appl. Sci. Technol., vol. 23, no. 3, pp. 1-26, Jun. 2023.
B. Goldfain et al., “Autorally: An open platform for aggressive autonomous driving,” IEEE Control Syst. Mag., vol. 39, no. 1, pp. 26-55, Jun. 2019.
S. Mehta, C. Paunwala, and B. Vaidya, “CNN based traffic sign classification using Adam optimizer,” in Proc. Int. Conf. Intell. Comput. Control Syst. (ICCS), 2019, pp. 1293-1298.
K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2016, pp. 770-778.
