Autonomous Driving Smart Car Based on Deep Learning
Article Sidebar
Main Article Content
Abstract
Road tracking as an essential task in autonomous driving is crucial for artificial intelligence. Most research is conducted in virtual environments, but it is vital to conduct practical experiments on real cars. The current researchers use toy cars for road track, but the toy cars can only drive at a fixed speed and a fixed angle for steering, which leads to reproduction errors during the experiment. We built a smart car based on a scale model using Jetson Nano as a mainboard, which can adjust the speed and steering gain to improve road tracking performance and reduce reproduction errors. To analyze the impact of hyperparameters, we conducted experiments on 48 autonomous driving models and proposed optimal hyperparameter configuration schemes, and trained the optimal autonomous driving model BH-ResNet. In addition, we also research the effect of the speed and steering gain on the performance of the smart car and propose an optimal gain value. Moreover, we compare BH-ResNet with other existing models, and BH-ResNet outperforms other models, scoring the highest in both tracks, with 94 and 90. Furthermore, the BH-ResNet model can also achieve road tracks with superior performance in unseen scenes, and our proposed model has excellent applicability and practicality.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
เนื้อหาข้อมูล
References
H. Fujiyoshi, T. Hirakawa, and T. J. I. R. Yamashita, “Deep Learning-Based Image Recognition for Autonomous Driving,” IATSS Research, vol. 43, no. 4, pp. 244-252, Dec. 2019.
S. Grigorescu, B. Trasnea, T. Cocias et al., “A Survey of Deep Learning Techniques for Autonomous Driving,” Journal of Field Robotics, vol. 37, no. 3, pp. 362-386, Apr. 2020.
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. 2018 IEEE International Conference on Artificial Intelligence and Virtual Reality(AIVR), 2018, pp. 262-266.
N. Hossain, M. T. Kabir, T. R. Rahman et al., “A Real-Time Surveillance Mini-Rover Based on Opencv-Python-JAVA Using Raspberry Pi 2,” in Proc. 2015 IEEE International Conference on Control System, Computing and Engineering(ICCSCE), 2015, pp. 476-481.
U. Karni, S. S. Ramachandran, K. Sivaraman et al., “Development of Autonomous Downscaled Model Car Using Neural Networks and Machine Learning,” in Proc. 2019 3rd International Conference on Computing Methodologies and Communication (ICCMC), 2019, pp. 1089-1094.
A. Banerjee, V. Bolar, A. Chaurasia et al., “Autonomous Driving Vehicle,” International Research Journal of Engineering and Technology, vol. 7, no. 4, pp. 6048-6050, Apr. 2020.
E. Yılmaz and S. T. Özyer. (2019, Jan.). Remote and Autonomous Controlled Robotic Car Based on Arduino with Real-Time Obstacle Detection and Avoidance. Universal Journal of Engineering Science. [Online]. 7(1), pp. 1-7. Available: http://earsiv.cankaya.edu.tr:8080/handle/handle/20.500.12416/4265
S. Yuenyong and Q. Jian, “Generating Synthetic Training Images for Deep Reinforcement Learning of a Mobile Robot,” Journal of Intelligent Informatics and Smart Technology, vol. 2, pp. 16-20, Mar. 2017.
T. D. Do, M. T. Duong, Q. V. Dang et al., “Real-Time SelfDriving Car Navigation Using Deep Neural Network,” in Proc. 2018 4th InternationalConference on Green Technology and Sustainable Development, 2018, pp. 7-12.
Q. Zhang, T. Du, and C. Tian. (2019, Dec. 20). Self-Driving Scale Car Trained by Deep Reinforcement Learning. [Online]. Available: https://arxiv.org2abs/1909.03467
Y. Li, J. Qu, and Technology, “Intelligent Road Tracking and Real-time Acceleration-deceleration for Autonomous Driving Using Modified Convolutional Neural Networks,” Current Applied Science and Technology, vol. 22, no. 6, p. 26, Mar. 2022.
V. Rausch, A. Hansen, E. Solowjow et al., “Learning a Deep Neural Net Policy for End-to-End Control of Autonomous Vehicles,” in Proc. 2017 American Control Conference, Seattle, WA, USA, 2017, pp. 4914-4919.
P. M. Radiuk, “Impact of Training Set Batch Size on the Performance of Convolutional Neural Networks for Diverse Datasets,” Information Technology and Management Science, vol. 20, no. 1, pp. 20-24, Dec. 2017.
M. Choi, “An Empirical Study on the Optimal Batch Size for the Deep Q-Network,” in Proc. International Conference on Robot Intelligence Technology and Applications, 2017, pp. 73-81.
S. Chowdhuri, T. Pankaj, and K. Zipser, “Multinet: Multi-Modal Multi-Task Learning for Autonomous Driving,” in Proc. 2019 IEEE Winter Conference on Applications of Computer Vision, 2019, pp. 1496-1504.
J. Kocić, N. Jovičić, and V. J. S. Drndarević, “An End-to-End Deep Neural Network for Autonomous Driving Designed for Embedded Automotive Platforms,” MDPI, vol. 19, no. 9, p. 2064, Apr. 2019.
A. Iqbal, S. S. Ahmed, M. D. Tauqeer et al., “Design of Multifunctional Autonomous Car Using Ultrasonic and Infrared Sensors,” in Proc. 2017 International Symposium on Wireless Systems and Networks (ISWSN), 2017, pp. 1-5.
K. Yu, L. Jia, Y. Chen et al., “Deep Learning: Yesterday, Today, and Tomorrow,” Journal of Computer Research and Development, vol. 50, no. 9, pp. 1799-1804, Sep. 2013.
Y. LeCun, Y. Bengio, and G. J. N. Hinton, “Deep Learning,” Nature, vol. 521, no. 7553, pp. 436-444, May. 2015.
J. Gu, Z. Wang, J. Kuen et al., “Recent Advances in Convolutional Neural Networks,” Pattern Recognition, vol. 77, pp. 354-377, May. 2018.
A. Karpathy, G. Toderici, S. Shetty et al., “Large-Scale Video Classification with Convolutional Neural Networks,” in Proc. IEEE Conference on Computer Vision and Pattern Recognition, 2014, pp. 1725-1732.
S. Albawi, T. A. Mohammed, and S. Al-Zawi, “Understanding of a Convolutional Neural Network,” in Proc. 2017 International Conference on Engineering and Technology, 2017, pp. 1-6.
S. J. I. S. Cass, “Nvidia Makes it Easy to Embed AI: The Jetson Nano Packs a Lot of Machine-Learning Power into DIY Projects,” IEEE Spectrum, vol. 57, no. 7, pp. 14-16, Jul. 2020.
R. Febbo, B. Flood, J. Halloy et al., (2020, Jul. 26). Autonomous Vehicle Control Using a Deep Neural Network and Jetson Nano. [Online]. Available: https://dl.acm.org/doi/abs/10.1145/3311790.3396669
P. Gupta, V. Singh, A. J. J. Parashar et al., “Smart Autonomous Vehicle Using End to End Learning,” Journal of Innovation in Computer Science and Engineering, vol. 9, no. 2, pp. 7-11, Jan. 2020.
G. Huang, Z. Liu, L. Van Der Maaten et al., “Densely Connected Convolutional Networks,” in Proc. IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA, July 21-26, 2017, pp. 4700-4708.
A. Krizhevsky, I. Sutskever, and G. E. Hinton, “Imagenet Classification with Deep Convolutional Neural Networks,” Advances in Neural Information Processing Systems, vol. 60, no. 6, pp. 84-90, Jun. 2017.