A comparison study of deep neural controllers and classic controllers in self-driving car application

Document Type : Research Article

Authors

1 Computer Architecture, Department od Computer Engineering, Isfahan, Iran

2 Computer Architecture, Computer Engineering Department, Isfahan, Iran

3 اصفهان-فنی و مهندسی- مهندسی مکانیک

4 Computer Architecture, Department of Computer Engineering, University of Isfahan, Isfahan, Iran

Abstract

In this paper deep neural controller is evaluated in self-driving car application which is one of the most important and critical among human-in-the-loop cyber physical systems. To this aim, the modern controller is compared with two classic controllers, i.e. proportional–integral–derivative and model predictive control for both quantitative and qualitative parameters. The parameters reflect three main challenges: (i) design-time challenges like dependency to the model and design parameters, (ii) implementation challenges including ease of implementation and computation workload, and (iii) run-time challenges and parameters covering performance in terms of speed, accuracy, control cost and effort, kinematic energy and vehicle depreciation. The main objective of our work is to present comparison and concrete metrics for designers to compare modern and traditional controllers. A framework for design, implementation and evaluation is presented. An end-to-end controller, constituting six convolution layers and four fully connected layers, is evaluated as the modern controller. The controller learns human driving behaviors and is used to drive the vehicle autonomously. Our results show that despite the main advantages of the controller i.e. being model free and also trainable, in terms of important metrics, this controller exhibits acceptable performance in comparison with proportional–integral–derivative and model predictive controllers.
 

Keywords

Main Subjects

References

[1] S.K. Khaitan, J.D. McCalley, Design techniques and applications of cyberphysical systems: A survey, IEEE Systems Journal, 9(2) (2014) 350-365.
[2] M. Jirgl, Z. Bradac, P. Fiedler, Human-in-the-loop issue in context of the cyber-physical systems, IFAC-PapersOnLine, 51(6) (2018) 225-230.
[3] I. Lenz, R.A. Knepper, A. Saxena, DeepMPC: Learning deep latent features for model predictive control, in:  Robotics: Science and Systems, Rome, Italy, 2015.
[4] Q. Zhu, T. Başar, Robust and resilient control design for cyber-physical systems with an application to power systems, in:  2011 50th IEEE Conference on Decision and Control and European Control Conference, IEEE, 2011, pp. 4066-4071.
[5] P.A. Ioannou, J. Sun, Robust adaptive control, Courier Corporation, 2012.
[6] J.-X. Xu, Y. Tan, Linear and nonlinear iterative learning control, Springer, 2003.
[7] S.M. Grigorescu, B. Trasnea, L. Marina, A. Vasilcoi, T. Cocias, Neurotrajectory: a neuroevolutionary approach to local state trajectory learning for autonomous vehicles, IEEE Robotics and Automation Letters, 4(4) (2019) 3441-3448.
[8] W. Liu, Z. Wang, X. Liu, N. Zeng, Y. Liu, F.E. Alsaadi, A survey of deep neural network architectures and their applications, Neurocomputing, 234 (2017) 11-26.
[9] A. Zappone, M. Di Renzo, M. Debbah, Wireless networks design in the era of deep learning: Model-based, AI-based, or both?, IEEE Transactions on Communications, 67(10) (2019) 7331-7376.
[10] G.E. Hinton, S. Osindero, Y.-W. Teh, A fast learning algorithm for deep belief nets, Neural computation, 18(7) (2006) 1527-1554.
[11] N. O’Mahony, S. Campbell, A. Carvalho, S. Harapanahalli, G.V. Hernandez, L. Krpalkova, D. Riordan, J. Walsh, Deep learning vs. traditional computer vision, in:  Science and Information Conference, Springer, 2019, pp. 128-144.
[12] S. Levine, C. Finn, T. Darrell, P. Abbeel, End-to-end training of deep visuomotor policies, The Journal of Machine Learning Research, 17(1) (2016) 1334-1373.
[13] R. Raina, A. Madhavan, A.Y. Ng, Large-scale deep unsupervised learning using graphics processors, in:  Proceedings of the 26th annual international conference on machine learning, 2009, pp. 873-880.
[14] D.A. Pomerleau, Alvinn: An autonomous land vehicle in a neural network, in:  Advances in neural information processing systems, 1989, pp. 305-313.
[15] U. Muller, J. Ben, E. Cosatto, B. Flepp, Y.L. Cun, Off-road obstacle avoidance through end-to-end learning, in:  Advances in neural information processing systems, 2006, pp. 739-746.
[16] M. Bojarski, A. Choromanska, K. Choromanski, B. Firner, L. Jackel, U. Muller, K. Zieba, Visualbackprop: efficient visualization of cnns, arXiv preprint arXiv:1611.05418,  (2016).
[17] M. Bojarski, A. Choromanska, K. Choromanski, B. Firner, L. Jackel, U. Muller, K. Zieba, Visualbackprop: visualizing cnns for autonomous driving, arXiv preprint arXiv:1611.05418, 2 (2016).
[18] M. Bojarski, D. Del Testa, D. Dworakowski, B. Firner, B. Flepp, P. Goyal, L.D. Jackel, M. Monfort, U. Muller, J. Zhang, End to end learning for self-driving cars, arXiv preprint arXiv:1604.07316,  (2016).
[19] Udacity, Public driving dataset, in, https://www.udacity.com/self-driving-car, 2020.
[20] J. Kong, M. Pfeiffer, G. Schildbach, F. Borrelli, Kinematic and dynamic vehicle models for autonomous driving control design, in:  2015 IEEE Intelligent Vehicles Symposium (IV), IEEE, 2015, pp. 1094-1099.
[21] Z. Wu, Y. Liu, G. Pan, A smart car control model for brake comfort based on car following, IEEE transactions on intelligent transportation systems, 10(1) (2008) 42-46.
[22] A. Mohammadi, Code repository, in, Github, https://github.com/abbasmohammadi/ETE, 2020.
[23] A. Mohammadi, Short video of our self-driving car, in, https://b2n.ir/738589, 2019.
Amirkabir Journal of Mechanical Engineering
Volume 53, Issue 4 (Special Issue)
July 2021
Pages 2439-2458

Files

Share

How to cite

Statistics