This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Open AccessArticle
Quadratic Programming Vision-Based Control of a Scale-Model Autonomous Vehicle Navigating in Intersections
by
Esmeralda Enriqueta Mascota Muñoz
Esmeralda Enriqueta Mascota Muñoz
Esmeralda Enriqueta Mascota Muñoz is pursuing the B. Eng. degree in Industrial Electronic Systems [...]
Esmeralda Enriqueta Mascota Muñoz is pursuing the B. Eng. degree in Industrial Electronic Systems Engineering at the Autonomous University of Mexico City. She has participated in diverse research projects and robotics competitions, and she has also authored conference papers, with one Best Paper Award achieved. Her research interests are automatic control theory and robotics.
,
Oscar González Miranda
Oscar González Miranda
Oscar Gonzalez Miranda received his Ph. D. degree in Automatic Control from the Research and Studies [...]
Oscar Gonzalez Miranda received his Ph. D. degree in Automatic Control from the Research and Advanced Studies Center of the National Polytechnic Institute, Mexico, in 2025. He currently works as lecturer at the Autonomous University of Mexico City. His research interests are machine learning, computer vision, and control of dynamic systems.
Xchel Ramos Soto
Xchel Ramos Soto
Xchel Ramos Soto is undergraduate student at the Industrial Electronic Systems Engineering program a [...]
Xchel Ramos Soto is undergraduate student at the Industrial Electronic Systems Engineering program of the Autonomous University of Mexico City. He undertook a research visit at the Research and Advanced Studies Center of the National Polytechnic Institute in 2025. His interests are PLC and microcontroller programming, robotics, and autonomous vehicles.
Juan Manuel Ibarra Zannatha
Juan Manuel Ibarra Zannatha
Juan Manuel Ibarra Zannatha received his Ph. D. degree in Robotics from the Institute for Research [...]
Juan Manuel Ibarra Zannatha received his Ph. D. degree in Robotics from the Institute for Research in Computer Science and Random Systems, France, in 1982. He has been full professor at the Research and Advanced Studies Center of the National Polytechnic Institute since 1982. He has authored numerous journal and conference papers, book chapters, and books. Currently, he is the Head of the Robotics and Computer Vision Laboratory at the Automatic Control Department of the same institution. His research topics mainly include the perception and control of autonomous robots.
Santos Miguel Orozco Soto
Santos Miguel Orozco Soto
Santos Miguel Orozco Soto received his Ph. D. degree in Automatic Control from the Research and of a [...]
Santos Miguel Orozco Soto received his Ph. D. degree in Automatic Control from the Research and Advanced Studies Center of the National Polytechnic Institute, Mexico, in 2020. He worked as postdoctoral researcher at the University of Naples Federico II from 2020 to 2022. Since 2023, he has been a full professor at the Autonomous University of Mexico City; currently, as of 2025, he is working as a visiting professor at the Free University of Bolzano. His research interests are control theory and its applications.
1
Science and Technology College, Autonomous University of Mexico City, Mexico City 06720, Mexico
2
Automatic Control Department, Research and Advanced Studies Center of the National Polytechnic Institute, Mexico City 07360, Mexico
3
Faculty of Engineering, Free University of Bolzano, 39100 Bolzano, Italy
*
Author to whom correspondence should be addressed.
Actuators 2025, 14(10), 494; https://doi.org/10.3390/act14100494 (registering DOI)
Submission received: 31 July 2025
/
Revised: 3 October 2025
/
Accepted: 4 October 2025
/
Published: 12 October 2025
Abstract
This paper presents an optimal control for autonomous vehicles navigating in intersection scenarios. The proposed controller is based on solving a Quadratic Programming optimization technique to provide a feasible control signal respecting actuator constraints. The proposed controller was implemented in a scale-sized vehicle and is executed using only on-board perception and computing systems to retrieve the state dynamics, i.e., an inertial measurement unit and a monocular camera, to compute the estimated states through intelligent computer vision algorithms. The stability of the error signals of the closed-loop system was proved both mathematically and experimentally, using standard performance indices for ten trials. The proposed technique was compared against LQR and MPC strategies, showing 67% greater accuracy than the LQR approach and 53.9% greater accuracy than the MPC technique, while turning during the intersection. Moreover, the proposed QP controller showed significantly greater efficiency by reducing the control effort by 63.3% compared to the LQR, and by a substantial 78.4% compared to the MPC. These successful results proved that the proposed controller is an effective alternative for autonomously navigating within intersection scenarios.
Share and Cite
MDPI and ACS Style
Muñoz, E.E.M.; Miranda, O.G.; Soto, X.R.; Zannatha, J.M.I.; Soto, S.M.O.
Quadratic Programming Vision-Based Control of a Scale-Model Autonomous Vehicle Navigating in Intersections. Actuators 2025, 14, 494.
https://doi.org/10.3390/act14100494
AMA Style
Muñoz EEM, Miranda OG, Soto XR, Zannatha JMI, Soto SMO.
Quadratic Programming Vision-Based Control of a Scale-Model Autonomous Vehicle Navigating in Intersections. Actuators. 2025; 14(10):494.
https://doi.org/10.3390/act14100494
Chicago/Turabian Style
Muñoz, Esmeralda Enriqueta Mascota, Oscar González Miranda, Xchel Ramos Soto, Juan Manuel Ibarra Zannatha, and Santos Miguel Orozco Soto.
2025. "Quadratic Programming Vision-Based Control of a Scale-Model Autonomous Vehicle Navigating in Intersections" Actuators 14, no. 10: 494.
https://doi.org/10.3390/act14100494
APA Style
Muñoz, E. E. M., Miranda, O. G., Soto, X. R., Zannatha, J. M. I., & Soto, S. M. O.
(2025). Quadratic Programming Vision-Based Control of a Scale-Model Autonomous Vehicle Navigating in Intersections. Actuators, 14(10), 494.
https://doi.org/10.3390/act14100494
Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details
here.
Article Metrics
Article metric data becomes available approximately 24 hours after publication online.
