Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 Mar 20;24(6):1985.
doi: 10.3390/s24061985.

A Novel Machine Learning-Based ANFIS Calibrated RISS/GNSS Integration for Improved Navigation in Urban Environments

Ahmed E Mahdi  1 , Ahmed Azouz  1 , Aboelmagd Noureldin  2 , Ashraf Abosekeen  1
Affiliations

A Novel Machine Learning-Based ANFIS Calibrated RISS/GNSS Integration for Improved Navigation in Urban Environments

Ahmed E Mahdi et al. Sensors (Basel). .

Abstract

Autonomous vehicles (AVs) require accurate navigation, but the reliability of Global Navigation Satellite Systems (GNSS) can be degraded by signal blockage and multipath interference in urban areas. Therefore, a navigation system that integrates a calibrated Reduced Inertial Sensors System (RISS) with GNSS is proposed. The system employs a machine-learning-based Adaptive Neuro-Fuzzy Inference System (ANFIS) as a novel calibration technique to improve the accuracy and reliability of the RISS. The ANFIS-based RISS/GNSS integration provides a more precise navigation solution in such environments. The effectiveness of the proposed integration scheme was validated by conducting tests using real road trajectory and simulated GNSS outages ranging from 50 to 150 s. The results demonstrate a significant improvement in 2D position Root Mean Square Error (RMSE) of 43.8% and 28% compared to the traditional RISS/GNSS and the frequency modulated continuous wave (FMCW) Radar (Rad)/RISS/GNSS integrated navigation systems, respectively. Moreover, an improvement of 47.5% and 23.4% in 2D position maximum errors is achieved compared to the RISS/GNSS and the Rad/RISS/GNSS integrated navigation systems, respectively. These results reveal significant improvements in positioning accuracy, which is essential for safe and efficient navigation. The long-term stability of the proposed system makes it suitable for various navigation applications, particularly those requiring continuous and precise positioning information. The ANFIS-based approach used in the proposed system is extendable to other low-end IMUs, making it an attractive option for a wide range of applications.

Keywords: ANFIS; GNSS; INS; INS/GNSS integration; MEMS-IMU; RISS; autonomous vehicle navigation; machine learning.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflicts of interest.

Figures

Figure 1
Figure 1
The basic structure of the ANFIS [50].
Figure 2
Figure 2
The training phase for the ML ANFIS model.
Figure 3
Figure 3
The validation phase of the ML ANFIS model.
Figure 4
Figure 4
The ML-based RISS block diagram.
Figure 5
Figure 5
A CDF comparison plot for the forward accelerometer error.
Figure 6
Figure 6
A CDF comparison plot for the transversal accelerometer error.
Figure 7
Figure 7
A CDF comparison plot for the vertical gyroscope error.
Figure 8
Figure 8
The ML-based RISS/GPS system block diagram.
Figure 9
Figure 9
The overall flowchart of the proposed methodology.
Figure 10
Figure 10
Interior test-bed showing the units involved in the experiment.
Figure 11
Figure 11
The reference trajectory with GNSS outage places and their numbers.
Figure 12
Figure 12
The gyroscope bias convergence time comparison.
Figure 13
Figure 13
Positioning performance during outage 1.
Figure 14
Figure 14
The azimuth comparison through outage 1.
Figure 15
Figure 15
A zoomed– in trajectory segment before outage 1.
Figure 16
Figure 16
Positioning performance during outage 3.
Figure 17
Figure 17
The azimuth comparison through outage 3.
Figure 18
Figure 18
Positioning performance during outage 5.
Figure 19
Figure 19
The azimuth comparison through outage 5.
Figure 20
Figure 20
2D position RMSE comparison.
Figure 21
Figure 21
2D position max error comparison.
Figure 22
Figure 22
Overall performance comparison.
See this image and copyright information in PMC

References

    1. Skog I., Händel P. In-car positioning and navigation technologiesa survey. IEEE Trans. Intell. Transp. Syst. 2009;10:4–21. doi: 10.1109/TITS.2008.2011712. - DOI
    1. Ayala R., Khan Mohd T. Sensors in Autonomous Vehicles: A Survey. J. Auton. Veh. Syst. 2021;1:1–16. doi: 10.1115/1.4052991. - DOI
    1. Šipoš M., Rohac J., Nováček P. Improvement of Electronic Compass Accuracy Based on Magnetometer and Accelerometer Calibration. Acta Phys. Pol. A. 2012;121:945–949. doi: 10.12693/APhysPolA.121.945. - DOI
    1. Angrisano A., Petovello M., Pugliano G. Benefits of Combined GPS/GLONASS with Low-Cost MEMS IMUs for Vehicular Urban Navigation. Sensors. 2012;12:5134–5158. doi: 10.3390/s120405134. - DOI - PMC - PubMed
    1. Aftatah M., Lahrech A., Abounada A. Fusion of GPS/INS/Odometer measurements for land vehicle navigation with GPS outage; Proceedings of the 2016 2nd International Conference on Cloud Computing Technologies and Applications (CloudTech); Marrakech, Morocco. 24–26 May 2016; Piscataway, NJ, USA: IEEE; 2016. pp. 48–55. - DOI

LinkOut - more resources