3D Gaussian Splatting for Robust Autonomous Navigation in Low-Texture Taxiway Environments

Jin Woo Baik, A. Lynn Abbott, Daniel R. Choate, Jason Rife, and Abhijit Sarkar

Peer Reviewed

Abstract: The rise in GNSS jamming and spoofing has created an urgent need for independent onboard navigation backups during aircraft taxiing. However, airfields are typically visually featureless: broad expanses of uniform asphalt with repetitive patterns and few distinctive landmarks. This lack of texture causes conventional monocular feature-based methods to suffer from scale ambiguity and geometric degeneracy. We present a vision-based navigation framework built on 3D Gaussian Splatting (3DGS). Standard 3DGS initializes its scene geometry from Structure-from-Motion (SfM), a feature-based reconstruction that inherits this same scale ambiguity on low-texture surfaces and forms a bottleneck for metric-accurate mapping. We replace SfM initialization with LiDAR initialization that anchors Gaussian ellipsoids to physical surfaces, enforcing absolute metric scale. LiDAR and RTK-GNSS are used only to build the reference map; the deployed aircraft navigates using a camera and the prebuilt map, and requires neither sensor during operation. The trained model is converted into a 2D occupancy grid through a domain-adaptive pipeline combining 2.5D elevation filtering with photometric segmentation. Across KITTI-360 and custom data from the Virginia Tech/Montgomery Executive Airport (KBCB), the benefit of the LiDAR prior proves strongly texture-dependent: marginal on KITTI-360 but decisive on KBCB, where it recovers physical geometry that a randomly initialized baseline cannot. Notably, on featureless taxiways the baseline achieves higher photometric scores yet far worse depth accuracy, showing that standard rendering metrics mask geometric errors the LiDAR prior corrects. In ROS 2 Navigation 2 (Nav2) taxiing simulations, the LiDAR-initialized map lowers trajectory, pose, and cross-track errors by three- to five-fold, establishing a scalable, GNSS-independent reference map for aircraft ground navigation.
Published in: Proceedings of the 39th International Technical Meeting of the Satellite Division of the Institute of Navigation (ION GNSS+ 2026)
September 14 - 18, 2026
Hyatt Regency Grand Cypress
Orlando, Florida
Pages: 304 - 318
Cite this article: Baik, Jin Woo, Abbott, A. Lynn, Choate, Daniel R., Rife, Jason, Sarkar, Abhijit, "3D Gaussian Splatting for Robust Autonomous Navigation in Low-Texture Taxiway Environments," Proceedings of the 39th International Technical Meeting of the Satellite Division of the Institute of Navigation (ION GNSS+ 2026), Orlando, Florida, September 2026, pp. 304-318. https://doi.org/10.33012/2026.20766
Full Paper:

Sign in to download with your ION membership, download credits or subscription, or buy this article.

Sign In Buy this article: $12 for ION members, $35 for non-members
References:
Show 31 references
  1. Bijelic, M., Gruber, T., Mannan, F., Kraus, F., Ritter, W., Dietmayer, K., & Heide, F. (2020). Seeing through fog without seeing fog: Deep multimodal sensor fusion in unseen adverse weather. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 11682-11692. https://doi.org/10.1109/cvpr42600.2020.01170
  2. Cadena, C., Carlone, L., Carrillo, H., Latif, Y., Scaramuzza, D., Neira, J., Reid, I., & Leonard, J. J. (2016). Past, present, and future of simultaneous localization and mapping: Toward the robust-perception age. IEEE Transactions on Robotics, 32(6), 1309-1332. https://doi.org/10.1109/tro.2016.2624754
  3. Cao, M., Liu, Z., Li, N., & Zhao, H. (2026). SpatioGS: Spatiotemporal-aware density control for dynamic scene rendering with Gaussian splatting. The Visual Computer, 42(5), 215. https://doi.org/10.1007/s00371-026-04442-w
  4. Chen, P., Zhao, X., Zeng, L., Liu, L., Liu, S., Sun, L., Li, Z., Chen, H., Liu, G., Qiao, Z., Qu, Y., Xu, D., Li, L., & Li, L. (2025). A review of research on SLAM technology based on the fusion of LiDAR and vision. Sensors, 25(5), 1447. https://doi.org/10.3390/s25051447
  5. Cheng, L., Qi, Z., Zhou, Z., Lu, C., & Xiong, G. (2025). LT-Gaussian: Long-term map update using 3D Gaussian splatting for autonomous driving. Proceedings of the IEEE Intelligent Vehicles Symposium (IV), 1427-1433.
  6. Choate, D., & Rife, J. H. (2025). Exploiting structure-from-motion for robust vision-based map matching for aircraft surface movement. Proceedings of the 38th International Technical Meeting of the Satellite Division of The Institute of Navigation (ION GNSS+ 2025), 1769-1783. https://doi.org/10.33012/2025.20382
  7. Delezenne, Q., Petrunin, I., Xu, Z., Neptune, J., & Bleakley, T. (2024). Autonomous navigation with taxiway crossings identification using camera vision and airport map. Proceedings of the AIAA SciTech 2024 Forum, 1300. https://doi.org/10.2514/6.2024-1300
  8. EASA & IATA. (2024, January 26). EASA partners with IATA to counter aviation safety threat from GNSS spoofing and jamming [Press release]. https://www.easa.europa.eu/en/newsroom-and-events/press-releases/easa-partners-iata-counteraviation-safety-threat-gnss-spoofing
  9. Engel, J., Schöps, T., & Cremers, D. (2014). LSD-SLAM: Large-scale direct monocular SLAM. Proceedings of the European Conference on Computer Vision (ECCV), 834-849.
  10. Ganeriwala, P., Alvarez, A., AlQahtani, A., Bhattacharyya, S., Khan, M. A. H., & Neogi, N. (2025). Runway vs. taxiway: Challenges in automated line identification and notation approaches. Proceedings of the IEEE International Systems Conference (SysCon), 1-8.
  11. Kerbl, B., Kopanas, G., Leimkühler, T., & Drettakis, G. (2023). 3D Gaussian splatting for real-time radiance field rendering. ACM Transactions on Graphics, 42(4), 139:1-139:14. https://doi.org/10.1145/3592433
  12. Lang, X., Li, L., Wu, C., Zhao, C., Liu, L., Liu, Y., Lv, J., & Zuo, X. (2025). Gaussian-LIC: Real-time photo-realistic SLAM with Gaussian splatting and lidar-inertial-camera fusion. Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), 8500-8507.
  13. Liu, Y., Luo, C., Fan, L., Wang, N., Peng, J., & Zhang, Z. (2024). CityGaussian: Real-time high-quality large-scale scene rendering with Gaussians. Proceedings of the European Conference on Computer Vision (ECCV), 265-282.
  14. Luiten, J., Kopanas, G., Leibe, B., & Ramanan, D. (2024). Dynamic 3D Gaussians: Tracking by persistent dynamic view synthesis. Proceedings of the International Conference on 3D Vision (3DV), 800-809. https://doi.org/10.1109/3dv62453.2024.00044
  15. Mildenhall, B., Srinivasan, P. P., Tancik, M., Barron, J. T., Ramamoorthi, R., & Ng, R. (2021). NeRF: Representing scenes as neural radiance fields for view synthesis. Communications of the ACM, 65(1), 99-106.
  16. Neamati, D., Dai, A., Partha, M., Legel, L., & Gao, G. (2025). Distributional robustness of learned features for 3D map localization. Proceedings of the 38th International Technical Meeting of the Satellite Division of The Institute of Navigation (ION GNSS+ 2025), 1975-1985. https://doi.org/10.33012/2025.20446
  17. Peng, Q., Xiang, Z., Fan, Y., Zhao, T., & Zhao, X. (2022). RWT-SLAM: Robust visual SLAM for highly weak-textured environments. arXiv: 2207.03539. https://doi.org/10.48550/arXiv.2207.03539
  18. Pitropov, M., Garcia, D. E., Rebello, J., Smart, M., Wang, C., Czarnecki, K., & Waslander, S. (2021). Canadian adverse driving conditions dataset. The International Journal of Robotics Research, 40(4-5), 681-690.
  19. Schönberger, J. L., & Frahm, J.-M. (2016). Structure-from-motion revisited. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 4104-4113. https://doi.org/10.1109/CVPR.2016.445
  20. Shan, T., Englot, B., Meyers, D., Wang, W., Ratti, C., & Rus, D. (2020). LIO-SAM: Tightly-coupled lidar inertial odometry via smoothing and mapping. Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 5135-5142.
  21. Suder, J., Stankiewicz, T., & Szczerbowski, K. (2025). Real-time detection of airport vertical signs using YOLOv8 and enhanced data augmentation strategies. Proceedings of the Signal Processing: Algorithms, Architectures, Arrangements, and Applications Conference (SPA), 291-296.
  22. Valentin, R., Katz, S. M., Carneiro, A. B., Walker, D., & Kochenderfer, M. J. (2025). Predictive uncertainty for runtime assurance of a real-time computer vision-based landing system. Proceedings of the AIAA DATC/IEEE 44th Digital Avionics Systems Conference (DASC), 1-8.
  23. Watanabe, Y., Manecy, A., Hiba, A., Nagai, S., & Aoki, S. (2019). Vision-integrated navigation system for aircraft final approach in case of GNSS/SBAS or ILS failures. Proceedings of the AIAA SciTech 2019 Forum, 0113. https://doi.org/10.2514/6 https://doi.org/10.2514/6.2019-0113
  24. 2019-0113 https://doi.org/10.2514/6.2019-0113
  25. Waymo. (2020, September). The Waymo driver handbook: How our highly-detailed maps help unlock new capabilities. https://waymo.com/blog/2020/09/the-waymo-driver-handbook-mapping/
  26. Wolkow, S., Angermann, M., Dekiert, A., & Bestmann, U. (2019). Model-based threshold and centerline detection for aircraft positioning during landing approach. Proceedings of the ION 2019 Pacific PNT Meeting, 767-776. https://doi.org/10.33012/2019.16787
  27. Wu, G., Yi, T., Fang, J., Xie, L., Zhang, X., Wei, W., Liu, W., Tian, Q., & Wang, X. (2024). 4D Gaussian splatting for real-time dynamic scene rendering. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 20310-20320.
  28. Xiao, R., Liu, W., Chen, Y., & Hu, L. (2024). LIV-GS: Lidar-vision integration for 3D Gaussian splatting SLAM in outdoor environments. IEEE Robotics and Automation Letters, 10(1), 421-428.
  29. Zeng, L., Zhao, B., Hu, J., Shen, X., Dang, Z., Bao, H., & Cui, Z. (2025). GaussianUpdate: Continual 3D Gaussian splatting update for changing environments. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 25800-25809.
  30. Zhang, J., & Singh, S. (2014). LOAM: Lidar odometry and mapping in real-time. Proceedings of Robotics: Science and Systems (RSS), 2, 1-9.
  31. Zotov, A. V., Lebedev, M. A., & Komarov, D. V. (2025). Neural network detection of runway and taxiway marking lines. Pattern Recognition and Image Analysis, 35(3), 455-467.