Budget-Efficient PID Tuning of a Line-Following Differential-Drive AGV Using Extra Trees Surrogate-Assisted CMA-ES

Authors

DOI:

https://doi.org/10.31436/iiumej.v27i3.4508

Keywords:

Automated Guided Vehicle, PID tuning, CMA-ES, Extra Trees Surrogate, Fixed-Budget Optimization

Abstract

Physical PID tuning for line-following automated guided vehicles (AGVs) is sample-inefficient because the gain-to-performance relationship is nonlinear and noisy, while every candidate must be executed on the real platform. Conventional population optimizers can therefore spend a limited experimental budget on unproductive trials, and evidence for surrogate-assisted CMA-ES under explicit true-evaluation accounting on embedded AGVs remains limited. This study evaluates an Extra Trees surrogate-assisted CMA-ES supervisory tuner on a single line-following differential-drive AGV. CMA-ES generates a virtual gain population in normalized space, and Extra Trees ranks it using the predicted objective and inter-tree dispersion; only a small, ranked subset undergoes physical evaluation. The objective combines integral absolute error, root mean square error, overshoot, actuation smoothness, and a lost-line penalty. We compared the method with pure CMA-ES, particle swarm optimization, and a genetic algorithm on Circle and 8Shape trajectories, using an identical budget of 57 true evaluations for every method, seed, and trajectory. The proposed method achieved the lowest mean final-best objective on both trajectories and improved on the strongest baseline by 30.8% on Circle and 20.8% on 8Shape. Cross-run distributions, empirical cumulative distribution functions, and time-domain responses support the same ranking. These results show that surrogate screening can improve sample efficiency for PID tuning on the tested embedded platform.

ABSTRAK: Penalaan PID secara fizikal bagi kenderaan berpandu automatik (AGV) pengikut garisan tidak cekap dari segi sampel kerana hubungan antara gandaan dan prestasi adalah tak linear serta bising, sedangkan setiap calon perlu diuji pada platform sebenar. Pengoptimum berasaskan populasi konvensional boleh menggunakan bajet eksperimen yang terhad pada percubaan yang kurang produktif, dan bukti bagi CMA-ES berbantukan surrogat dengan perakaunan penilaian sebenar yang jelas pada AGV terbenam masih terhad. Kajian ini menilai penala penyeliaan CMA-ES berbantukan surrogat Extra Trees pada sebuah prototaip AGV pacuan kebezaan pengikut garisan. CMA-ES menjana populasi gandaan maya dalam ruang ternormal dan Extra Trees menyusunnya menggunakan objektif ramalan dan sebaran antara pokok, manakala hanya subset kecil dengan skor terbaik menjalani penilaian fizikal. Fungsi objektif menggabungkan ralat mutlak bersepadu, ralat punca min kuasa dua, limpahan, kelancaran aktuasi, dan penalti kehilangan garisan. Kaedah ini dibandingkan dengan CMA-ES tulen, pengoptimuman kawanan zarah, dan algoritma genetik pada trajektori Circle dan 8Shape menggunakan bajet yang sama, iaitu 57 penilaian sebenar bagi setiap kaedah, benih rawak, dan trajektori. Kaedah yang dicadangkan mencapai purata objektif terbaik akhir terendah pada kedua-dua trajektori serta mengatasi garis dasar terbaik sebanyak 30.8% pada Circle dan 20.8% pada 8Shape. Taburan antara larian, fungsi taburan kumulatif empirik, dan respons domain masa menyokong kedudukan yang sama. Dapatan ini menunjukkan bahawa penapisan surrogat dapat meningkatkan kecekapan sampel bagi penalaan PID pada platform terbenam yang diuji.

Downloads

Download data is not yet available.

References

Oyekanlu EA, et al. (2020) A review of recent advances in automated guided vehicle technologies: Integration challenges and research areas for 5G-based smart manufacturing applications. IEEE Access, 8:202312-202353.

Dos Reis WPN, Couto GE, Junior OM. (2023) Automated guided vehicles position control: A systematic literature review. Journal of Intelligent Manufacturing, 34(4):1483-1545.

Alwan MMA, Green AA, Noori AS, Aldair AA. (2021) Design and implementation of line follower Arduino mobile robot using Matlab Simulink toolbox. Iraqi Journal for Electrical and Electronic Engineering, 17(2):11-16.

Moshayedi AJ, Abbasi A, Liao L, Li S. (2019) Path planning and trajectory tracking of a mobile robot using bio-inspired optimization algorithms and PID control. 2019 IEEE International Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications (CIVEMSA), 1-6.

Moshayedi AJ, et al. (2022) Simulation and validation of optimized PID controller in AGV (Automated Guided Vehicles) model using PSO and BAS algorithms. Computational Intelligence and Neuroscience, 2022(1):7799654.

Henclová K. (2019) Using CMA-ES for tuning coupled PID controllers within models of combustion engines. Neural Network World, 29(5):325-344.

Chen JC, Chen TL, Teng YC. (2021) Meta-model based simulation optimization for automated guided vehicle system under different charging mechanisms. Simulation Modelling Practice and Theory, 106:102208.

Krawczyk K, Arabas J. (2025) Single-objective surrogate models for continuous metaheuristics: An overview. Applied Sciences, 15(16):9068.

Patil RS, Jadhav SP, Patil MD. (2024) Review of intelligent and nature-inspired algorithms-based methods for tuning PID controllers in industrial applications. Journal of Robotics and Control (JRC), 5(2):336-358.

Aliskan I. (2025) The optimization-based fuzzy logic controllers for autonomous ground vehicle path tracking. Engineering Applications of Artificial Intelligence, 151:110642.

Yu J, Liang M, Peng W, Wu T, Rong C, Zhang D. (2023) Speed control based on an improved PID controller with BP neural network for two wheel differential AGV system. 2023 IEEE 6th Student Conference on Electric Machines and Systems (SCEMS), 1-5.

Ha VT, Thuong TT, Truc LN. (2024) Trajectory tracking control based on genetic algorithm and proportional integral derivative controller for two-wheel mobile robot. Bulletin of Electrical Engineering and Informatics, 13(4):2348-2357.

Demir MH, Demirok M. (2023) Designs of particle-swarm-optimization-based intelligent PID controllers and DC/DC buck converters for PEM fuel-cell-powered four-wheeled automated guided vehicle. Applied Sciences, 13(5):2919.

Jangid P, Nagar V, Sharma A, Nagar S, Palwalia DK. (2025) Design a PID controller based on grey wolf optimization algorithm for single-area load frequency control. Journal of Emerging Science and Engineering, 3(1):e36-e36.

Mosaad AM, Attia MA, Abdelaziz AY. (2019) Whale optimization algorithm to tune PID and PIDA controllers on AVR system. Ain Shams Engineering Journal, 10(4):755-767.

Van Niekerk JA, le Roux JD, Craig IK. (2023) On-line automatic controller tuning of a multivariable grinding mill circuit using Bayesian optimisation. Journal of Process Control, 128:103008.

Tumpach J, Koza J, Hole?a M. (2023) Improving optimization with Gaussian processes in the covariance matrix adaptation evolution strategy. ITAT'23: Information Technologies – Applications and Theory, 3498(10).

Khouzani FF, Mirzaei A, Plante PL, Gewali L. (2025) CMA-ES with radial basis function surrogate for black-box optimization. ITNG 2025. Advances in Intelligent Systems and Computing. 1463:367-379.

Bujgoi G, Sendrescu D. (2025) Tuning of PID controllers using reinforcement learning for nonlinear system control. Processes, 13(3):735.

Van Niekerk JA, le Roux JD, Craig IK. (2025) Reinforcement learning based automatic tuning of PID controllers in multivariable grinding mill circuits. Control Engineering Practice, 165:106522.

Downloads

Published

2026-09-11

How to Cite

Mastang, Taha, B. A., Apsari, R., Mukhlisin, M., Dwi Wardihani, E., & Arsad, N. (2026). Budget-Efficient PID Tuning of a Line-Following Differential-Drive AGV Using Extra Trees Surrogate-Assisted CMA-ES. IIUM Engineering Journal, 27(3), 481–504. https://doi.org/10.31436/iiumej.v27i3.4508

Issue

Section

Mechatronics and Automation Engineering