Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
156 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

NeuRSS: Enhancing AUV Localization and Bathymetric Mapping with Neural Rendering for Sidescan SLAM (2405.05807v1)

Published 9 May 2024 in cs.RO

Abstract: Implicit neural representations and neural rendering have gained increasing attention for bathymetry estimation from sidescan sonar (SSS). These methods incorporate multiple observations of the same place from SSS data to constrain the elevation estimate, converging to a globally-consistent bathymetric model. However, the quality and precision of the bathymetric estimate are limited by the positioning accuracy of the autonomous underwater vehicle (AUV) equipped with the sonar. The global positioning estimate of the AUV relying on dead reckoning (DR) has an unbounded error due to the absence of a geo-reference system like GPS underwater. To address this challenge, we propose in this letter a modern and scalable framework, NeuRSS, for SSS SLAM based on DR and loop closures (LCs) over large timescales, with an elevation prior provided by the bathymetric estimate using neural rendering from SSS. This framework is an iterative procedure that improves localization and bathymetric mapping. Initially, the bathymetry estimated from SSS using the DR estimate, though crude, can provide an important elevation prior in the nonlinear least-squares (NLS) optimization that estimates the relative pose between two loop-closure vertices in a pose graph. Subsequently, the global pose estimate from the SLAM component improves the positioning estimate of the vehicle, thus improving the bathymetry estimation. We validate our localization and mapping approach on two large surveys collected with a surface vessel and an AUV, respectively. We evaluate their localization results against the ground truth and compare the bathymetry estimation against data collected with multibeam echo sounders (MBES).

Definition Search Book Streamline Icon: https://streamlinehq.com
References (31)
  1. R. Li and S. Pai, “Improvement of bathymetric data bases by shape from shading technique using side-scan sonar images,” in Proc. IEEE OCEANS Conf., vol. 1, Honololu, HI, USA, 1991, pp. 320–324.
  2. D. Langer and M. Hebert, “Building qualitative elevation maps from side scan sonar data for autonomous underwater navigation,” in Proc. IEEE Int. Conf. Robot. Autom., 1991, pp. 2478–2483 vol.3.
  3. A. E. Johnson and M. Hebert, “Seafloor map generation for autonomous underwater vehicle navigation,” Auton. Robots, vol. 3, no. 2, pp. 145–168, 1996.
  4. E. Coiras, Y. Petillot, and D. M. Lane, “Multiresolution 3-D reconstruction from side-scan sonar images,” IEEE Trans. Image Process., vol. 16, no. 2, pp. 382–390, 2007.
  5. Y. Xie, N. Bore, and J. Folkesson, “Bathymetric reconstruction from sidescan sonar with deep neural networks,” IEEE J. Ocean. Eng., vol. 48, no. 2, pp. 372–383, 2023.
  6. ——, “Neural network normal estimation and bathymetry reconstruction from sidescan sonar,” IEEE J. Ocean. Eng., vol. 48, no. 1, pp. 218–232, 2023.
  7. N. Bore and J. Folkesson, “Neural shape-from-shading for survey-scale self-consistent bathymetry from sidescan,” IEEE J. Ocean. Eng., vol. 48, no. 2, pp. 416–430, 2022.
  8. Y. Xie, N. Bore, and J. Folkesson, “Sidescan only neural bathymetry from large-scale survey,” Sensors, vol. 22, no. 14, p. 5092, 2022.
  9. M. Qadri, M. Kaess, and I. Gkioulekas, “Neural implicit surface reconstruction using imaging sonar,” in Proc. IEEE Int. Conf. Robot. Autom.   IEEE, 2023, pp. 1040–1047.
  10. Y. Xie, G. Troni, N. Bore, and J. Folkesson, “Bathymetric surveying with imaging sonar using neural volume rendering,” arXiv preprint arXiv:2404.14819, 2024.
  11. I. Torroba, C. I. Sprague, N. Bore, and J. Folkesson, “PointNetKL: Deep inference for GICP covariance estimation in bathymetric SLAM,” IEEE Robot. Automat. Lett., vol. 5, no. 3, pp. 4078–4085, 2020.
  12. T. A. Huang and M. Kaess, “Towards acoustic structure from motion for imaging sonar,” in Proc. IEEE/RSJ Int. Conf. Intell. Robots Syst.   IEEE, 2015, pp. 758–765.
  13. ——, “Incremental data association for acoustic structure from motion,” in Proc. IEEE/RSJ Int. Conf. Intell. Robots Syst.   IEEE, 2016, pp. 1334–1341.
  14. E. Westman, A. Hinduja, and M. Kaess, “Feature-based SLAM for imaging sonar with under-constrained landmarks,” in Proc. IEEE Int. Conf. Robot. Autom.   IEEE, 2018, pp. 3629–3636.
  15. E. Westman and M. Kaess, “Degeneracy-aware imaging sonar simultaneous localization and mapping,” IEEE J. Ocean. Eng., vol. 45, no. 4, pp. 1280–1294, 2019.
  16. J. Wang, T. Shan, and B. Englot, “Underwater terrain reconstruction from forward-looking sonar imagery,” in Proc. IEEE Int. Conf. Robot. Autom., 2019, pp. 3471–3477.
  17. M. F. Fallon, M. Kaess, H. Johannsson, and J. J. Leonard, “Efficient AUV navigation fusing acoustic ranging and side-scan sonar,” in Proc. IEEE Int. Conf. Robot. Autom.   IEEE, 2011, pp. 2398–2405.
  18. L. Bernicola, D. Gueriot, and J.-M. Le Caillec, “A hybrid registration approach combining SLAM and elastic matching for automatic side-scan sonar mosaic,” in Proc. IEEE OCEANS Conf.   IEEE, 2014, pp. 1–5.
  19. M. Issartel, D. Guériot, N. Aouf, and J.-M. Le Caillec, “Robust SLAM for side scan sonar image mosaicking,” in Proc. IEEE OCEANS Conf.   IEEE, 2017, pp. 1–10.
  20. Y. Xu, R. Zheng, S. Zhang, and M. Liu, “Robust inertial-aided underwater localization based on imaging sonar keyframes,” IEEE Trans. Instrum. Meas., vol. 71, pp. 1–12, 2022.
  21. J. Zhang, Y. Xie, L. Ling, and J. Folkesson, “A fully-automatic side-scan sonar simultaneous localization and mapping framework,” IET Radar, Sonar & Navigation, pp. 1–10, 2023.
  22. I. T. Ruiz, Y. Petillot, and D. M. Lane, “Improved AUV navigation using side-scan sonar,” in Proc. MTS/IEEE OCEANS Conf., vol. 3.   IEEE, 2003, pp. 1261–1268.
  23. I. T. Ruiz, S. de Raucourt, Y. Petillot, and D. M. Lane, “Concurrent mapping and localization using sidescan sonar,” IEEE J. Ocean. Eng., vol. 29, no. 2, pp. 442–456, 2004.
  24. S. Reed, I. T. Ruiz, C. Capus, and Y. Petillot, “The fusion of large scale classified side-scan sonar image mosaics,” IEEE Trans. Image Process., vol. 15, no. 7, pp. 2049–2060, 2006.
  25. J. Zhang, Y. Xie, L. Ling, and J. Folkesson, “A dense subframe-based SLAM framework with side-scan sonar,” arXiv preprint arXiv:2312.13802, 2023.
  26. V. Sitzmann, J. Martel, A. Bergman, D. Lindell, and G. Wetzstein, “Implicit neural representations with periodic activation functions,” Adv. Neural Inf. Process. Syst., vol. 33, 2020.
  27. N. Bore and J. Folkesson, “Neural shape-from-shading for survey-scale self-consistent bathymetry from sidescan,” IEEE J. Ocean. Eng., vol. 48, no. 2, pp. 416–430, 2023.
  28. B. Mildenhall, P. P. Srinivasan, M. Tancik, J. T. Barron, R. Ramamoorthi, and R. Ng, “NeRF: Representing scenes as neural radiance fields for view synthesis,” in Proc. Eur. Conf. Comput. Vis.   Springer, 2020, pp. 405–421.
  29. P. Wang, L. Liu, Y. Liu, C. Theobalt, T. Komura, and W. Wang, “NeuS: Learning neural implicit surfaces by volume rendering for multi-view reconstruction,” Adv. Neural Inf. Process. Syst., vol. 34, pp. 27 171–27 183, 2021.
  30. M. Kaess, H. Johannsson, R. Roberts, V. Ila, J. J. Leonard, and F. Dellaert, “iSAM2: Incremental smoothing and mapping using the bayes tree,” Int. J. Robot. Res., vol. 31, no. 2, pp. 216–235, 2012.
  31. N. Bore and J. Folkesson, “Modeling and simulation of sidescan using conditional generative adversarial network,” IEEE J. Ocean. Eng., vol. 46, no. 1, pp. 195–205, 2021.
Citations (1)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now