Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

GPS-IMU Sensor Fusion for Reliable Autonomous Vehicle Position Estimation

Simegnew Yihunie Alaba

TL;DR

This work addresses reliable vehicle positioning when GPS signals are degraded by proposing a GNSS-IMU fusion framework implemented with an Unscented Kalman Filter. The approach leverages high-rate IMU data for continuous motion estimates and GNSS corrections for absolute positioning, with sigma-point prediction and nonlinear measurement updates. Validation on the KITTI GNSS/IMU dataset demonstrates significant RMSE reductions in all axes compared to GNSS-only results, highlighting improved robustness in GPS-denied environments. The findings support the practical deployment of UKF-based sensor fusion for safer and more reliable autonomous vehicle navigation, with future work pointing to multi-sensor extensions such as LiDAR or radar.

Abstract

Global Positioning System (GPS) navigation provides accurate positioning with global coverage, making it a reliable option in open areas with unobstructed sky views. However, signal degradation may occur in indoor spaces and urban canyons. In contrast, Inertial Measurement Units (IMUs) consist of gyroscopes and accelerometers that offer relative motion information such as acceleration and rotational changes. Unlike GPS, IMUs do not rely on external signals, making them useful in GPS-denied environments. Nonetheless, IMUs suffer from drift over time due to the accumulation of errors while integrating acceleration to determine velocity and position. Therefore, fusing the GPS and IMU is crucial for enhancing the reliability and precision of navigation systems in autonomous vehicles, especially in environments where GPS signals are compromised. To ensure smooth navigation and overcome the limitations of each sensor, the proposed method fuses GPS and IMU data. This sensor fusion uses the Unscented Kalman Filter (UKF) Bayesian filtering technique. The proposed navigation system is designed to be robust, delivering continuous and accurate positioning critical for the safe operation of autonomous vehicles, particularly in GPS-denied environments. This project uses KITTI GNSS and IMU datasets for experimental validation, showing that the GNSS-IMU fusion technique reduces GNSS-only data's RMSE. The RMSE decreased from 13.214, 13.284, and 13.363 to 4.271, 5.275, and 0.224 for the x-axis, y-axis, and z-axis, respectively. The experimental result using UKF shows promising direction in improving autonomous vehicle navigation using GPS and IMU sensor fusion using the best of two sensors in GPS-denied environments.

GPS-IMU Sensor Fusion for Reliable Autonomous Vehicle Position Estimation

TL;DR

This work addresses reliable vehicle positioning when GPS signals are degraded by proposing a GNSS-IMU fusion framework implemented with an Unscented Kalman Filter. The approach leverages high-rate IMU data for continuous motion estimates and GNSS corrections for absolute positioning, with sigma-point prediction and nonlinear measurement updates. Validation on the KITTI GNSS/IMU dataset demonstrates significant RMSE reductions in all axes compared to GNSS-only results, highlighting improved robustness in GPS-denied environments. The findings support the practical deployment of UKF-based sensor fusion for safer and more reliable autonomous vehicle navigation, with future work pointing to multi-sensor extensions such as LiDAR or radar.

Abstract

Global Positioning System (GPS) navigation provides accurate positioning with global coverage, making it a reliable option in open areas with unobstructed sky views. However, signal degradation may occur in indoor spaces and urban canyons. In contrast, Inertial Measurement Units (IMUs) consist of gyroscopes and accelerometers that offer relative motion information such as acceleration and rotational changes. Unlike GPS, IMUs do not rely on external signals, making them useful in GPS-denied environments. Nonetheless, IMUs suffer from drift over time due to the accumulation of errors while integrating acceleration to determine velocity and position. Therefore, fusing the GPS and IMU is crucial for enhancing the reliability and precision of navigation systems in autonomous vehicles, especially in environments where GPS signals are compromised. To ensure smooth navigation and overcome the limitations of each sensor, the proposed method fuses GPS and IMU data. This sensor fusion uses the Unscented Kalman Filter (UKF) Bayesian filtering technique. The proposed navigation system is designed to be robust, delivering continuous and accurate positioning critical for the safe operation of autonomous vehicles, particularly in GPS-denied environments. This project uses KITTI GNSS and IMU datasets for experimental validation, showing that the GNSS-IMU fusion technique reduces GNSS-only data's RMSE. The RMSE decreased from 13.214, 13.284, and 13.363 to 4.271, 5.275, and 0.224 for the x-axis, y-axis, and z-axis, respectively. The experimental result using UKF shows promising direction in improving autonomous vehicle navigation using GPS and IMU sensor fusion using the best of two sensors in GPS-denied environments.
Paper Structure (5 sections, 19 equations, 4 figures, 1 table)

This paper contains 5 sections, 19 equations, 4 figures, 1 table.

Table of Contents

  1. Introduction
  2. Literature Review
  3. Method
  4. Experiments
  5. Conclusion

Figures (4)

  • Figure 1: The proposed architecture.
  • Figure 2: Position errors in x, y, and z-coordinates using GNSS only.
  • Figure 3: Position errors in x, y, and z-coordinates using fusion of GNSS and IMU.
  • Figure 4: Positions in meters at GNSS frequency of 1 Hz.