Trajectory Tracking Control Using Evolutionary Approaches for Autonomous Driving

Abstract

Capitalizing on the strides in artificial intelligence and the escalating demand for safer and more efficient traffic systems, the investigation unveils a trio of evolutionary algorithms - namely Grey Wolf Optimizer (GWO), Multi-Verse Optimizer (MVO) and Salp Swarm Algorithm (SSA) - in the context of hyperparameter calibration for the Proportional-Integral-Derivative (PID) controller. Revered for their classical simplicity and widespread industrial use, PID controllers are pivotal in feedback control systems, ensuring desired system performance through meticulous parameter adjustments. This research introduces a novel application of GWO, MVO, and SSA in the realm of PID control, aiming to optimize the controllers' parameters. To exemplify the utility of the proposed algorithms, two distinct trajectory scenarios are employed as target trajectories. Rigorous numerical evaluations, accompanied by graphical analyses, showcase the prowess of these algorithms in steering the trajectory tracking process. By pioneering the application of these optimizers in the PID controller domain, this investigation not only demonstrates their superior performance over traditional methods but also contributes to the broader field of control engineering by suggesting a more efficient approach to traffic system optimization. This exploration also paves the way for further research into leveraging advanced optimization techniques to elevate the safety and efficiency of traffic systems.

Keywords

• Autonomous driving
• Evolutionary algorithms
• PID
• Trajectory tracking control

References

1. [1] Farag W. Complex Trajectory Tracking Using PID Control for Autonomous Driving. Int J Intell Transp Syst Res. 2020; 18(2): 356-366. https://doi.org/10.1007/s13177-019-00204-2
2. [2] Farag W, Saleh Z. Tuning of PID Track Followers for Auton-omous Driving. Presented at International Conference on In-novation and Intelligence for Informatics Computing, and Technologies; 2018; Sakhier, Bahrain. 10.1109/3ICT.2018.8855773
3. [3] De Luca A, Oriol G, Samson C. Feedback Control of a Non-holonomic Car-like Robot. Robot Motion Planning and Con-trol. 2005; 171-253.
4. [4] Sebastian B, Ben-Tzvi P. Physics Based Path Planning for Autonomous Tracked Vehicle in Challenging Terrain. J Intell Robot Syst. 2019; 95: 511-526. https://doi.org/10.1007/s10846-018-0851-3
5. [5] Hu J, Tao J, Zhao W, Han Y. Modeling and Simulation of Steering Control Strategy for Dual-motor Coupling Drive Tracked Vehicle. J Braz Soc Mech Sci Eng. 2019; 41: 1-11. https://doi.org/10.1007/s40430-019-1692-0
6. [6] Zhai L, Sun TM, Wang QN, Wang J. Lateral Stability Control of Dynamic Steering for Dual Motor Drive High Speed Tracked Vehicle. Int J Automot Technol. 2016; 17: 1079-1090. https://doi.org/10.1007/s12239-016-0105-y
7. [7] Chu D, Li H, Zhao C, Zhou T. Trajectory Tracking of Auton-omous Vehicle Based on Model Predictive Control with PID Feedback. IEEE trans Intell Transp Syst. 2022; 24(2): 2239-2250. https://doi.org/10.1109/TITS.2022.3150365
8. [8] Tan KK, Qing-Guo W, Chieh HC. Advances in PID Control. Springer-Verlag; 1999.

9. [9] Kuyu YÇ, Vatansever F. Advanced Metaheuristic Algorithms on Solving Multimodal Functions: Experimental Analyses and Performance Evaluations. Arch Comput Methods Eng. 2021; 28: 4861–4873. https://doi.org/10.1007/s11831-021-09555-0
10. [10] Kuyu YÇ, Vatansever F. GOZDE: A Novel Metaheuristic Algorithm for Global Optimization. Future Gener Comput Syst. 2022; 136: 128-152. https://doi.org/10.1016/j.future.2022.05.022
11. [11] Yu T, Zhu H. Hyper-parameter optimization: A review of algorithms and applications. arXiv preprint 2020; arXiv: 2003.05689. https://doi.org/10.48550/arXiv.2003.05689
12. [12] Kuyu, YÇ, Onieva E, Lopez-Garcia P. A Hybrid Optimizer Based on Backtracking Search and Differential Evolution for Continuous Optimization. J Exp Theor Artif Intell. 2022; 34(3): 355-385. https://doi.org/10.1080/0952813X.2021.1872109
13. [13] P Zhao, J Chen, Y Song, X Tao, T Xu, T Mei. Design of a Control System for an Autonomous Vehicle Based on Adap-tive-PID. Int J Adv Robot Syst. 2012; 9(2): 44. https://doi.org/10.5772/51314
14. [14] Mirjalili S, Mirjalili SM, Lewis A. Grey Wolf Optimizer. Adv Eng Softw. 2014; 69: 46-61. https://doi.org/10.1016/j.advengsoft.2013.12.007
15. [15] Mirjalili S, Mirjalili SM, Hatamlou A. Multi-verse Optimizer: A Nature-inspired Algorithm for Global Optimization. Neural Comput Appl. 2016; 27: 495-513. https://doi.org/10.1007/s00521-015-1870-7
16. [16] Mirjalili S, Gandomi AH, Mirjalili SZ, Saremi S, Faris H, Mir-jalili SM. Salp Swarm Algorithm: A Bio-inspired Optimizer for Engineering Design Problems. Adv Eng Softw. 2017; 114: 163-191. https://doi.org/10.1016/j.advengsoft.2017.07.002
17. [17] Barzegar A, Doukhi O, Lee DJ. Design and Implementation of an Autonomous Electric Vehicle for Self-driving Control Un-der GNSS-denied Environments. Appl Sci. 2021; 11(8): 3688. https://doi.org/10.3390/app11083688
18. [18] Hanilçi F, Kuyu YÇ, Vatansever F. Optimizing Autonomous Path Tracking Using Population-Based Metaheuristic and Pure Pursuit Control. Presented at 14th International Conference on Electrical and Electronics Engineering. 2023; Bursa, Türkiye. https://doi.org/10.1109/ELECO60389.2023.10415995
19. [19] BaniHani S, De S. Development of a Genetic Algorithm‐based Lookup Table Approach for Efficient Numerical Integration in the Method of Finite Spheres with Application to the Solu-tion of Thin Beam and Plate Problems. Int J Numer Methods Eng. 2006; 67(12): 1700-1729. https://doi.org/10.1002/nme.1678
20. [20] Xu Z, Zhao W, Wang C. Local Path Planning and Tracking Control of Vehicle Collision Avoidance System. Trans Nan-jing Univ Aeronaut. 2018; 35(4): 729–738. http://dx.doi.org/10.16356/j.1005-1120.2018.04.729
21. [21] Johnson MA, Moradi MH. PID Control. London, UK: Spring-er-Verlag London Limited; 2005.
22. [22] Vatansever F, Hacıiskenderoğlu E. PID Tuning with Up-to-date Metaheuristic Algorithms. Uludağ University Journal of the Faculty of Engineering. 2022; 27(2): 573-584. https://doi.org/10.17482/uumfd.1090766
23. [23] Vatansever F, Sen D. Design of PID Controller Simulator Based on Genetic Algorithm. Uludağ University Journal of The Faculty of Engineering. 2013; 18(2): 7-18. https://doi.org/10.17482/uujfe.33406