Motorcycle Adaptive Cruise Control Using Model Predictive Control with Integrated Sensor Fusion
International Journal of Robotics and Control Systems · 08.01.2026 · 5 (6) · 3413-3434
DOI: 10.31763/ijrcs.v5i6.2113 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Robotics and Control Systems, online erschienen am 08.01.2026. Verfasst von Muiz Mahmud Zaim und 5 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-SA 4.0).
Abstract (Originalsprache)
Motorcycle safety remains a critical challenge due to the inherent instability and complex dynamics of two-wheeled vehicles, particularly in longitudinal control and car-following scenarios. This study addresses this challenge by developing a Motorcycle Adaptive Cruise Control (MACC) system based on Model Predictive Control (MPC), specifically tailored to motorcycle dynamics. The research contribution is the integration of longitudinal and lateral MPC control with a sensor fusion framework to manage speed regulation, safe following distance, and path-following under motorcycle-specific constraints. The proposed system employs MPC to predict future vehicle states and compute optimal acceleration and steering commands while respecting safety, comfort, and stability constraints. Radar- and vision-based sensor fusion is used to estimate relative distance, relative velocity, and lane geometry, providing reliable perception inputs for the controller. A comprehensive MATLAB/Simulink simulation framework is developed to evaluate system performance under straight-road, curved-road, and mixed-traffic scenarios, including lane changes and vehicle cut-ins. Simulation results demonstrate accurate velocity tracking, consistent maintenance of safe inter-vehicle distances, and stable path-following performance, with lateral deviations remaining below 0.5 m on straight segments and 1.2 m on curved paths. Longitudinal acceleration remains within predefined comfort limits, indicating smooth control behavior. The integrated controller adapts effectively to dynamic traffic conditions while maintaining safety margins. The findings confirm the feasibility of MPC-based MACC for motorcycles under simulated conditions. However, the results are limited to simulation-based validation, and real-world deployment will require further investigation of computational feasibility, sensor uncertainties, and experimental testing. This work contributes toward the development of scalable and reliable adaptive cruise control systems for motorcycle autonomy.
Zitieren
APA
Zaim, M. M., Toha, S. F., Mohamed, M. A., Abdullah, M., Rahman, M. A., & Hassan, M. H. (2026). Motorcycle Adaptive Cruise Control Using Model Predictive Control with Integrated Sensor Fusion. International Journal of Robotics and Control Systems, 5(6), 3413-3434. https://doi.org/10.31763/ijrcs.v5i6.2113
Vancouver
Zaim MM, Toha SF, Mohamed MA, Abdullah M, Rahman MA, Hassan MH. Motorcycle Adaptive Cruise Control Using Model Predictive Control with Integrated Sensor Fusion. International Journal of Robotics and Control Systems. 2026;5(6):3413-3434. doi:10.31763/ijrcs.v5i6.2113
BibTeX
@article{Zaim2026,
author = {Zaim, Muiz Mahmud and Toha, Siti Fauziah and Mohamed, Mawada Ahmed and Abdullah, Muhammad and Rahman, Md Ataur and Hassan, Masjuki Haji},
title = {Motorcycle Adaptive Cruise Control Using Model Predictive Control with Integrated Sensor Fusion},
journal = {International Journal of Robotics and Control Systems},
year = {2026},
volume = {5},
number = {6},
pages = {3413--3434},
doi = {10.31763/ijrcs.v5i6.2113}
}
EUVIMED