Design of a ROS-based Autonomous Navigation Correction System for Small Vehicles based on Visual Error Correction

Hongyu Pang

doi:10.6919/ICJE.202609_12(9).0021

Authors

Hongyu Pang Taiyuan University of Science and Technology, Taiyuan 030024, Shanxi, China

DOI:

https://doi.org/10.6919/ICJE.202609_12(9).0021

Keywords:

ROS Robot Car; Autonomous Navigation; Cumulative Error; Visual Correction; Feature Matching; Trajectory Correction.

Abstract

Addressing the issues of cumulative positioning errors in traditional ROS smart cars that rely on odometry for navigation, such as trajectory deviation, path deviation, and eventual navigation failure during long-distance travel, this paper designs and implements a vision-based real-time error correction navigation system.The system utilizes ROS as its development platform, retains the original odometer track calculation function, and introduces a visual feature matching and correction module. By matching the real-time collected environmental image features with reference templates, it calculates the lateral deviation and heading deviation of the vehicle online, and dynamically corrects the accumulated drift of the odometer.The experimental results show that the uncorrected system accumulates errors continuously and deviates severely from the trajectory during long-distance driving. After incorporating visual correction, the car can identify position deviations in real-time and correct them, significantly improving positioning accuracy and trajectory conformity. This effectively solves the navigation offset problem caused by differential odometer drift. The system is lightweight and easy to deploy, suitable for long-term stable autonomous navigation of indoor ROS mobile robots.

Downloads

Download data is not yet available.

References

[1] B. Al-Tawil, T. Hempel, A. Abdelrahman, & A. Al-Hamadi. (2024). A review of visual SLAM for robotics: evolution, properties, and future applications. Frontiers in Robotics and AI, 11, 1347985. [https://doi.org/10.3389/frobt.2024.1347985](https://doi.org/10.3389/frobt.2024.1347985)

[2] Shi, K., He, S., Shi, Z., Chen, A., & Xiong, Z. (2025). Radar and camera fusion for object detection and tracking: A comprehensive survey. IEEE Communications Surveys & Tutorials, 27(2), 1–35.

[3] Or, B., & Klein, I. (2022). A hybrid model and learning-based adaptive navigation filter. IEEE Transactions on Instrumentation and Measurement, 71, 1–11. Article 2516311. [https://doi.org/10.1109/TIM.2022.3197775](https://doi.org/10.1109/TIM.2022.3197775)

[4] Lu, C. X., Saputra, M. R. U., Zhao, P., Almalioglu, Y., De Gusmao, P. P., Chen, C., Sun, K., Trigoni, N., & Markham, A. (2020). milliEgo: Single-chip mmWave radar aided egomotion estimation via deep sensor fusion. In Proceedings of the 18th ACM Conference on Embedded Networked Sensor Systems (SenSys) (pp. 109–122).

[5] Teper, H., Betz, T., Günzel, M., Ebner, D., Von Der Brüggen, G., Betz, J., & Chen, J. (2025). Reconciling ROS 2 with classical real-time scheduling of periodic tasks. In Proceedings of the IEEE 31st Real-Time and Embedded Technology and Applications Symposium (RTAS) (pp. 177–189). [https://doi.org/10.1109/RTAS65571.2025.00027](https://doi.org/10.1109/RTAS65571.2025.00027)

[6] Casini, D., Blaß, T., Lütkebohle, I., & Brandenburg, B. B. (2022). A survey of real-time support, analysis, and advancements in ROS 2. Leibniz Transactions on Embedded Systems, 1(1), 42:1–42:34.

[7] Ye, Y. L., Nie, Z. G., Liu, X. J., Xie, F. G., Li, Z. H., & Li, P. (2023). ROS2 real-time performance optimization and evaluation. Chinese Journal of Mechanical Engineering, 36(1), 144. [https://doi.org/10.1186/s10033-023-00976-5](https://doi.org/10.1186/s10033-023-00976-5)

[8] Aniceto, S. B. P., Jr., McGrath, R. V. S., Ochengco, C. J. I., Regalado, M. G., & Chua, A. Y. (2020). A Novel Low-Cost Obstacle Avoidance System for a Quadcopter UAV Using Fuzzy Logic. International Journal of Mechanical Engineering and Robotics Research, 9(5), 733–738. [https://doi.org/10.18178/ijmerr.9.5.733-738](https://doi.org/10.18178/ijmerr.9.5.733-738)

[9] Tsutada, R., Hoang, T.-T., & Pham, C.-K. (2022). An Obstacle Avoidance Two-Wheeled Self-Balancing Robot. International Journal of Mechanical Engineering and Robotics Research, 11(1), 1–7. [https://doi.org/10.18178/ijmerr.11.1.1-7](https://doi.org/10.18178/ijmerr.11.1.1-7)