Abstract
Making autonomous driving a safe, feasible, and better alternative is one of the core problems the world is facing today. The horizon of the applications of AI and deep learning has changed the perspective of the human mind. Initially, what used to be thought of as the subtle impossible task is applicable today, and that too in the feasibly efficient way. Computer vision tasks powered with highly tuned CNNs are outperforming humans in many fields. Introductory implementations of the autonomous vehicle were merely achieved using raw image processing, and hard programmed rule-based logic systems along with machine/deep learning were used as secondary objective handlers. With the autonomous driving method proposed by Nvidia, the usability of CNNs is more adequate, adaptable, and applicable. In this paper, we propose the ensemble implementation of CNN-based regression models for autonomous driving. We have taken simulator generated driving view image dataset along with a mapped file of steering angle in radians. After applying image pre-processing and augmentation, we have used two CNN models along with their ensemble and compared their performance to minimize the risks of unsafe driving. We have compared Nvidia proposed CNN, MobileNet-V2 as regression model and Ensemble-M results for comparison of their respective performance, MSE scores and compute time to process. In result analysis, the MobileNet-V2 model performs better in densely featured roads and the Nvidia model performs better in sparsely featured roads, whereas Ensemble-M normalizes the performance of both models and efficiently results in the least MSE score (0.0201) with the highest computation time utilization making autonomous driving better, safer alternative.
Similar content being viewed by others
References
Alexeev VF, Staravoitau AI, Piskun GA, Likhacheuski DV (2018) End to end learning for a driving simulator. Дoклaды Бeлopyccкoгo гocyдapcтвeннoгo yнивepcитeтa инфopмaтики и paдиoэлeктpoники, 2(112)
Ali Alheeti KM, Gruebler A, McDonald-Maier K (2016) Intelligent intrusion detection of grey hole and rushing attacks in self-driving vehicular networks. Computers 5(3):16
Babiker MA, Elawad MA, Ahmed AH (2019) convolutional neural network for a self-driving car in a virtual environment. In: 2019 International conference on computer, control, electrical, and electronics engineering (ICCCEEE).pp 1–6. IEEE
Badue C, Guidolini R, Carneiro RV, Azevedo P, Cardoso VB, Forechi A, De Souza AF (2020) Self-driving cars: a survey. Exp Syst Appl, p 113816
Bechtel MG, McEllhiney E, Kim M, Yun H (2018) Deeppicar: a low-cost deep neural network-based autonomous car. In: 2018 IEEE 24th international conference on embedded and real-time computing systems and applications (RTCSA). pp 11–21. IEEE
Blyth PL, Mladenovic MN, Nardi BA, Ekbia HR, Su NM (2016) Expanding the design horizon for self-driving vehicles: Distributing benefits and burdens. IEEE Technol Soc Mag 35(3):44–49
Bojarski M, Del Testa D, Dworakowski D, Firner B, Flepp B, Goyal P, Jackel LD, Monfort M, Muller U, Zhang J, Zieba K (2016) End to end learning for self-driving cars. arXiv preprint http://arxiv.org/abs/1604.07316
Brooks R (2017) The big problem with self-driving cars is people. IEEE spectrum: technology, engineering, and science News
Chen SC (2019) Multimedia for autonomous driving. IEEE Multimedia 26(3):5–8
Chen Z, Huang X (2017) End-to-end learning for lane keeping of self-driving cars. In 2017 IEEE Intelligent Vehicles Symposium (IV). pp 1856–1860. IEEE
Chen C, Demir E, Huang Y, Qiu R (2021) The adoption of self-driving delivery robots in last mile logistics. Transp Res Part E Logist Transp Rev 146:102214
Chishti SO, Riaz S, BilalZaib M, Nauman M (2018) Self-driving cars using CNN and Q-learning. In: 2018 IEEE 21st International Multi-Topic Conference (INMIC). pp 1–7. IEEE
Chopra R, Roy SS (2020) End-to-end reinforcement learning for self-driving car. Advanced computing and intelligent engineering. Springer, Singapore, pp 53–61
Da Conceicao MA, Degadwala S (2020) Steering angle prediction based on road direction using convolution neural network (CNN)
Daily M, Medasani S, Behringer R, Trivedi M (2017) Self-driving cars. Computer 50(12):18–23
del Egio J, Bergasa LM, Romera E, Huélamo CG, Araluce J, Barea R (2018) Self-driving a car in simulation through a CNN. Workshop of physical agents. Springer, Cham, pp 31–43
Drews P, Williams G, Goldfain B, Theodorou EA, Rehg JM (2017) Aggressive deep driving: model predictive control with a cnn cost model. arXiv preprint http://arxiv.org/abs/1707.05303
Faas SM, Baumann M (2019) Light-based external human machine interface: color evaluation for self-driving vehicle and pedestrian interaction. In: Proceedings of the human factors and ergonomics society annual meeting. vol 63, no 1, pp 1232–1236. SAGE Publications, Los Angeles
Garimella G, Funke J, Wang C, Kobilarov M (2017) Neural network modeling for steering control of an autonomous vehicle. In: 2017 IEEE/RSJ international conference on intelligent robots and systems (IROS). pp 2609–2615. IEEE
Goodall NJ (2016) Can you program ethics into a self-driving car? IEEE Spectr 53(6):28–58
Hossain S, Fayjie AR, Doukhi O, Lee DJ (2018) CAIAS simulator: self-driving vehicle simulator for AI research. In: International conference on intelligent computing and optimization. pp 187–195. Springer, Cham
Hsieh W (2017) First order driving simulator (Doctoral dissertation, Master’s thesis, EECS Department, University of California, Berkeley)
Jhung J, Bae I, Moon J, Kim T, Kim J, Kim S (2018)End-to-end steering controller with cnn-based closed-loop feedback for autonomous vehicles. In: 2018 IEEE intelligent vehicles symposium (IV). pp 617–622. IEEE
Lehnert L, Tellex S, Littman ML (2017) Advantages and limitations of using successor features for transfer in reinforcement learning. arXiv preprint http://arxiv.org/abs/1708.00102.
Mori K, Fukui H, Murase T, Hirakawa T, Yamashita T, Fujiyoshi H (2019) Visual explanation by attention branch network for end-to-end learning-based self-driving. In: 2019 IEEE intelligent vehicles symposium (IV). pp 1577–1582. IEEE
Ndikumana A, Tran NH, Kim KT, Hong CS (2020) Deep learning based caching for self-driving cars in multi-access edge computing. IEEE Trans Intell Transp Syst
Ni J, Chen Y, Chen Y, Zhu J, Ali D, Cao W (2020) A survey on theories and applications for self-driving cars based on deep learning methods. Appl Sci 10(8):2749
Ohn-Bar E, Trivedi MM (2016) Looking at humans in the age of self-driving and highly automated vehicles. IEEE Trans Intell Veh 1(1):90–104
Olaverri-Monreal C (2020) Promoting trust in self-driving vehicles. Nature Electronics 3(6):292–294
Oluwatosin HS (2014) Client-server model. IOSRJ. Comput Eng 16(1):2278–8727
Ouyang Z, Niu J, Liu Y, Guizani M (2019) Deep CNN-based real-time traffic light detector for self-driving vehicles. IEEE Trans Mob Comput 19(2):300–313
Paden B, Čáp M, Yong SZ, Yershov D, Frazzoli E (2016) A survey of motion planning and control techniques for self-driving urban vehicles. IEEE Trans Intell Veh 1(1):33–55
Pearah PJ (2017) Opening the door to self-driving cars: how will this change the rules of the road. J High Tech l 18:38
Qiu T, Huang Z (2019) Learning a steering decision policy for end-to-end control of autonomous vehicle. In: 2019 5th international conference on control, automation and robotics (ICCAR). pp 347–351. IEEE
Sattler T, Zhou Q, Pollefeys M, Leal-Taixe L (2019) Understanding the limitations of cnn-based absolute camera pose regression. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 3302–3312
Savelsbergh MW, Sol M (1995) The general pickup and delivery problem. Transp Sci 29(1):17–29
Shalamov V, Filchenkov A, Shalyto A (2016) Genetic search of pickup and delivery problem solutions for self-driving taxi routing. In: IFIP international conference on artificial intelligence applications and innovations, pp 348–355. Springer, Cham
Smith RG, Eckroth J (2017) Building AI applications: Yesterday, today, and tomorrow. AI Mag 38(1):6–22
Smolyakov MV, Frolov AI, Volkov VN, Stelmashchuk IV (2018) Self-driving car steering angle prediction based on deep neural network an example of CarND udacity simulator. In: 2018 IEEE 12th international conference on application of information and communication technologies (AICT). pp 1–5. IEEE
Urmson C (2008) Self-driving cars and the urban challenge. IEEE Intell Syst 23(2):66–68
Valiente R, Zaman M, Ozer S, Fallah YP (2019) Controlling steering angle for cooperative self-driving vehicles utilizing cnn and lstm-based deep networks. In: 2019 IEEE intelligent vehicles symposium (IV). pp 2423–2428. IEEE
Viswanath P, Nagori S, Mody M, Mathew M, Swami P (2018) End to end learning based self-driving using JacintoNet. In 2018 IEEE 8th International Conference on Consumer Electronics-Berlin (ICCE-Berlin). pp 1–4. IEEE
Wang Y, Liu D, Jeon H, Chu Z, Matson ET (2019) End-to-end learning approach for autonomous driving: a convolutional neural network model. In ICAART (2), pp 833–839.
Wang YE, Wei GY, Brooks D (2019) Benchmarking tpu, gpu, and cpu platforms for deep learning. arXiv preprint http://arxiv.org/abs/1907.10701.
West DM (2016) Moving forward: self-driving vehicles in China, Europe, Japan, Korea, and the United States. Center for Technology Innovation at Brookings, Washington
Xia H, Yang H (2018) Is last-mile delivery a’killer app’for self-driving vehicles? Commun ACM 61(11):70–75
Zeng W, Wang S, Liao R, Chen Y, Yang B, Urtasun R (2020) Dsdnet: deep structured self-driving network. In European conference on computer vision, pp 156–172. Springer, Cham
Funding
This research received no external funding.
Author information
Authors and Affiliations
Contributions
All authors conceived and designed the study. MG and VU conducted the experiments, analyzed the data, and wrote the paper. All authors contributed to manuscript revision. All authors approved the final version of the manuscript and agree to be held accountable for the content therein.
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflicts of interest to report regarding the present study.
Ethical approval
No agency or research center is involved in this research.
Informed consent
The authors declare that they do not have any conflict of interest. This research does not involve any human or animal participation. All authors have checked and agreed with the submission.
Additional information
Communicated by Vicente Garcia Diaz.
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Gupta, M., Upadhyay, V., Kumar, P. et al. Implementation of autonomous driving using Ensemble-M in simulated environment. Soft Comput 25, 12429–12438 (2021). https://doi.org/10.1007/s00500-021-05954-4
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00500-021-05954-4