https://doi.org/10.26706/ijceae.6.3.20250602

---

Abstract:-

Recent developments in self-driving cars and smart control would make the idea of an autonomous vehicle a viable one. Nonetheless, using of such cars in traffic and some other hostile surroundings successful requires effective solution of a package of navigation, vision, and control problems. In all this, our ultimate goal is to come up with cost effective methods that are operationally sound which in turn can help the larger research community to take self-driving automobiles offering business potential seriously. However, what we are in need of, is a ploy that could transform the traditional motorists into discouraging using self-driving cars and at the same time works out the sorting of the present passenger cars into the future research work. In this vein, the current discussion develops a modular mechanical structure that could be manufactured in especially fast fashion and adapted on a significant portion of modern automobiles. The design brief is an intermediate stage of development on the road to the production of wholly autonomous cars. With the use of commercially available actuators, we prove that it is possible to transform homegrown automobiles of the sort found in abundance in the parking lot of whatever rest stop or convenience store you happen to drop by, quite reasonably to include most of the privately owned vehicles, into autonomous models. In the context of the motor vehicle's automation, motors are often used as actuators Considering the fact that the electro-mechanical motors did not work, pneumatic system was introduced to make one predetermined step automated. Mechanical setup of autonomous cars is the most important aspect and should provide a possibility to make regular updates as the car is designed to work under extremely changing conditions. In order to measure the feasibility of such strategy, two further convolutional neural networks were re-implemented, allowing to conduct an objective comparison of the performance, technical severity and architecture of the proposed system with regards to the reference networks. The architecture is proposed to 300 AlexNet units and three PilotNet units (Increased feature extraction capacity, slightly reduced control model replication ) and operate at a bigger scale than the prevalent models of neural networks that are available today. On the one hand, it has fewer architectural complexities compared to its peers and hence experiences longer latencies, and slower inference time; on the other hand, the system still ranks equally well on the autonomous-driving metrics reported by two similar benchmarks. By meeting this performance objective and at the cost of no longer requesting high-speed computing hardware, the model promotes not only cost-efficiency, scale, and total affordability.

Index Terms:-

Deep neural network, end-to-end learning, embedded systems, machine learning, camera, autonomous driving, and convolutional neural network

---

REFERENCES

1. LeCun Y., Bottou L., Bengio Y., Haffner P. “Gradient-Based Learning Applied to Document Recognition”:2020.
   

---

2. Simard D., Steinkraus P.Y., Platt J.C. “Best practices for convolutional neural networks applied to visual document analysis”:2021.
   

---

3. Shin H., Roth H., Gao M., Lu L., Xu Z., Nogues I., Yao J., Mollura D., Summers R. “Deep Convolutional Neural Networks for Computer-Aided Detection”: CNN Architectures, Dataset Characteristics and Transfer Learning:2020.
   

---

4. Pathak D., Krähenbühl P., Donahue J., Darrell T., Efros A.A. Context Encoders: “Feature Learning by Inpainting”:2021.
   

---

5. Karpathy A., Toderici G., Shetty S., Leung T., Sukthankar R., Li F.-F. “Large-Scale Video Classification with Convolutional Neural Networks”:2000.
   

---

6. Chi J., Kim H.-C, “Prediction of Arctic Sea Ice Concentration Using a Fully Data Driven Deep Neural Network”:2019.
   

---

7. Russakovsky O., Deng J., Su H., Krause J., Satheesh S., Ma S., Berg A.C. “Imagenet large scale visual recognition challenge”:2000.
   

---

8. Simonyan K., Zisserman A. “Very deep convolutional networks for large-scale image recognition”:2018.
   

---

9. Szegedy C., Liu W., Jia Y., Sermanet P., Reed S., Anguelov D., Erhan D., Vanhoucke V., Rabinovich A. May.23.2022.
   

---

10. He K., Zhang X., Ren S., Sun J. “Deep residual learning for image recognition”.2019.
    

---

11. Visin F., Kastner K., Cho K., Matteucci M., Courville A., Bengio Y. Renet: “A recurrent neural network-based alternative to convolutional networks”. 2000.
    

---

12. Zoph B., Vasudevan V., Shlens J., Le Q.V. “Learning Transferable Architectures for Scalable Image Recognition”. 2021.
    

---

13. Acuna D., Ling H., Kar A., Fidler S. “Efficient Interactive Annotation of Segmentation Datasets with Polygon-RNN++”.Mar.16.2022.
    

---

14. Wang T.C., Liu M.Y., Zhu J.Y., Liu G., Tao A., Kautz J., Catanzaro B. “Video-to-video synthesis”.Nov.5.2023.
    

---

15. Bojarski M., Del Testa D., Dworakowski D., Firner B., Flepp B., Goyal P., Jackel L., Monfort M., Muller U., Zhang J., et al. “End to end learning for self-driving cars”. 2021
    

---

16. Bojarski M., Yeres P., Choromanska A., Choromanski K., Firner B., Jackel L., Muller U. “Explaining how a deep neural network trained with end-to-end learning steers a car”.2000.
    

---

17. Mehta A., Adithya S., Anbumani S. “Learning end-to-end autonomous driving using guided auxiliary supervision”. 2019.
    

---

18. Chen Y., Wang J., Li J., Lu C., Luo Z., Xue H., Wang C. “LiDAR-Video Driving Dataset: Learning Driving Policies Effectively”.Jan.8.2023.
    

---

19. Ramezani Dooraki A., Lee D.-J. “An End-to-End Deep Reinforcement Learning-Based Intelligent Agent Capable of Autonomous Exploration in Unknown Environments”.Jun.3.2022.
    

---

20. Krizhevsky A., Sutskever I., Hinton G.E. “Imagenet classification with deep convolutional neural networks”. 2023.
    

---

21. Udacity, Inc. “Self-Driving Car Simulator”. [(accessed on 5 November 2018)].
    

---

22. Goodfellow I., Bengio Y., Courville A. “Deep Learning”. The MIT Press; Cambridge, MA, USA: 2020.
    

---

23. Aggarwal C.C. “Neural Networks and Deep Learning. Springer International Publishing; Cham, Switzerland”.2021.
    

---

24. Chollet F. “Deep Learning with Python. Manning Publications”; Shelter Island, NY, USA: 2021.
    

---

25. Sutton R.S., Barto A.G. “Reinforcement Learning”, The MIT Press; Cambridge, MA, USA: 2020.
    

---

26. LeCun Y., Boser B., Denker J.S., Henderson D., Howard R.E., Hubbard W., Jackel L.D. “Back propagation applied to handwritten zip code recognition”. May.23.2023.
    

---

27. P. Goodman, “Advantages and disadvantages of driverless cars,” Nov. 22 2022.
    

---

28. A. A. Jose, C. A. S. Pillai et al., “A novel approach for scheduling and routing of the self-guided vehicles in mesh topology using velocity control and alternate path techniques,” 2021.
    

---

29. J. M. Anderson, “Self-driving vehicles offer potential benefits, policy challenges for lawmakers,” Jan. 6 2019.
    

---

30. Geem, M.H.,On strongly continuous ρh-semigroup,Journal of Physics: Conference Series, 2019, 1234(1), https://doi:10.1088/1742-6596/1234/1/012109 .
    

---

31. Geem, M.H.,Hassan, A.R.,Neamah, H.I., 0-Semigroup of g-transformation Journal of Interdisciplinary Mathematics , 2025, 28(1), pp. 311–316.
    

---

32. Alsaeedi, A.H., Al-Mahmood, H.H.R., Alnaseri, Z.F. et al. Fractal feature selection model for enhancing high-dimensional biological problems. BMC Bioinformatics 25, 12 (2024). https://doi.org/10.1186/s12859-023-05619-z .
    

---

33. Shaimaa H.Mohammad, Israa Z. Chyad Alrikabi, Hayder Rahm Dakheel al- fayyadh, “Number Plate Recognition System Based on an Improved Segmentation Method”, International Journal of Computational and Electronic Aspects in Engineering, RAME Publishers, vol. 6, issue 1, pp. 42-50, 2025. https://doi.org/10.26706/ijceae.6.1.20250207 .
    

---

34. Serri Ismael Hamad, “Utilizing Convolutional Neural Networks for the Identification of Lung Cancer”, International Journal of Computational and Electronic Aspects in Engineering, vol. 6, issue 1, pp. 35-41,2025. https://doi.org/10.26706/ijceae.6.1.20250206.
    

---

35. Hiyam Hatem, “improved deep learning models for plants diseases detection for smart farming”, international journal of computational and electronic aspects in engineering, vol. 6, issue 1,pp. 10-21, 2025. https://doi.org/10.26706/ijceae.6.1.20250204 .
    

---

To view full paper, Download here

---