Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
158 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

Feature Space Exploration For Planning Initial Benthic AUV Surveys (2105.11598v2)

Published 25 May 2021 in cs.RO and cs.LG

Abstract: Special-purpose Autonomous Underwater Vehicles (AUVs) are utilised for benthic (seafloor) surveys, where the vehicle collects optical imagery of the seafloor. Due to the small-sensor footprint of the cameras and the vast areas to be surveyed, these AUVs can not feasibly collect full coverage imagery of areas larger than a few tens of thousands of square meters. Therefore it is necessary for AUV paths to sample the surveys areas sparsely, yet effectively. Broad-scale acoustic bathymetric data is readily available over large areas, and is often a useful prior of seafloor cover. As such, prior bathymetry can be used to guide AUV data collection. This research proposes methods for planning initial AUV surveys that efficiently explore a feature space representation of the bathymetry, in order to sample from a diverse set of bathymetric terrain. This will enable the AUV to visit areas that likely contain unique habitats and are representative of the entire survey site. We propose several information gathering planners that utilise a feature space exploration reward, to plan freeform paths or to optimise the placement of a survey template. The suitability of these methods to plan AUV surveys is evaluated based on the coverage of the feature space and also the ability to visit all classes of benthic habitat on the initial dive. Informative planners based on Rapidly-expanding Random Trees (RRT) and Monte-Carlo Tree Search (MCTS) were found to be the most effective. This is a valuable tool for AUV surveys as it increases the utility of initial dives. It also delivers a comprehensive training set to learn a relationship between acoustic bathymetry and visually-derived seafloor classifications.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (50)
  1. Multi-modal active perception for information gathering in science missions. Autonomous Robots, 43(7):1–20.
  2. Measurement maximizing adaptive sampling with risk bounding functions. 33rd AAAI Conference on Artificial Intelligence, AAAI 2019, 31st Innovative Applications of Artificial Intelligence Conference, IAAI 2019 and the 9th AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2019, pages 7511–7519.
  3. Autonomous exploration of large-scale benthic environments. Proceedings - IEEE International Conference on Robotics and Automation, pages 390–396.
  4. Benthic habitat mapping: A review of progress towards improved understanding of the spatial ecology of the seafloor using acoustic techniques. Estuarine, Coastal and Shelf Science, 92(3):502–520.
  5. A survey of Monte Carlo tree search methods. IEEE Transactions on Computational Intelligence and AI in Games, 4(1):1–43.
  6. Using Remote Sensing and in situ Measurements for Efficient Mapping and Optimal Sampling of Coral Reefs. Frontiers in Marine Science, 8(September):1–17.
  7. Sparus II AUV - A Hovering Vehicle for Seabed Inspection. IEEE Journal of Oceanic Engineering, 43(2):344–355.
  8. Pareto Monte Carlo Tree Search for Multi-Objective Informative Planning. In Robotics: Science and Systems 2019, Freiburg im Breisgau.
  9. Hierarchical probabilistic regression for AUV-based adaptive sampling of marine phenomena. Proceedings - IEEE International Conference on Robotics and Automation, pages 5571–5578.
  10. Choosing between strategies for designing surveys: Autonomous underwater vehicles. Methods in Ecology and Evolution, 5(3):287–297.
  11. Spatially balanced designs for transect-based surveys. Methods in Ecology and Evolution, 11(1):95–105.
  12. Multi-Scale Measures of Rugosity, Slope and Aspect from Benthic Stereo Image Reconstructions. PLoS ONE, 7(12).
  13. Selective Sampling for Example-based Word Sense Disambiguation. Computational Linguistics, 24(4):573–597.
  14. Deep Active Learning Over the Long Tail. arXiv, (m):1–10.
  15. Icebreaker: Element-wise Active Information Acquisition with Bayesian Deep Latent Gaussian Model. In Advances in Neural Information Processing Systems 32, pages 14820–14831. Curran Associates, Inc.
  16. Adaptive continuous-space informative path planning for online environmental monitoring. Journal of Field Robotics, 34(8):1427–1449.
  17. Sampling-based robotic information gathering algorithms. International Journal of Robotics Research, 33(9):1271–1287.
  18. Horn, B. K. (1981). Hill Shading and the Reflectance Map. Proceedings of the IEEE, 69(1):14–47.
  19. Sampling-based incremental information gathering with applications to robotic exploration and environmental monitoring. International Journal of Robotics Research, 38(6):658–685.
  20. Anytime motion planning using the RRT. Proceedings - IEEE International Conference on Robotics and Automation, pages 1478–1483.
  21. Probabilistic roadmaps for path planning in high-dimensional configuration spaces. IEEE Transactions on Robotics and Automation, 12(4):566–580.
  22. An introduction to variational autoencoders. Foundations and Trends in Machine Learning, 12(4):307–392.
  23. Bandit Based Monte-Carlo Planning. In Machine Learning: ECML 2006, pages 282–293.
  24. Non-myopic Planetary Exploration Combining in Situ and Remote Measurements. IEEE International Conference on Intelligent Robots and Systems, pages 536–543.
  25. Near-optimal sensor placements in Gaussian processes: Theory, efficient algorithms and empirical studies. Journal of Machine Learning Research, 9:235–284.
  26. Deep learning. Nature, 521(7553):436–444.
  27. Initial results of rover localization and topographic mapping for the 2003 mars exploration rover mission. Photogrammetric Engineering and Remote Sensing, 71(10):1129–1142.
  28. Mahalanobis, P. C. (1936). On the generilised distance in statistics. Proceedings of the National Institute of Sciences of India, pages 49–55.
  29. Active learning using pre-clustering. Proceedings, Twenty-First International Conference on Machine Learning, ICML 2004, pages 623–630.
  30. NSW Department of Planning Industry and Environment (2018). NSW Marine LiDAR Topo-Bathy 2018 Geotif. Technical report, NSW Government.
  31. Monte Carlo planning for active object classification. Autonomous Robots, 42(2):391–421.
  32. OR Tools. Google, Mountain View, California.
  33. Research and development in agricultural robotics: A perspective of digital farming. International Journal of Agricultural and Biological Engineering, 11(4):1–11.
  34. Multimodal learning and inference from visual and remotely sensed data. International Journal of Robotics Research, 36(1):24–43.
  35. Reynolds, D. (2009). Gaussian Mixture Models. Encyclopedia of biometrics, 741(2):1–5.
  36. Adaptive Informative Path Planning Using Deep Reinforcement Learning for UAV-based Active Sensing.
  37. Learning internal representations by error propagation. In Parallel Distributed Processing. MIT Press, Cambridge, MA, 1 edition.
  38. Active learning for convolutional neural networks: A core-set approach. In International Conference on Learning Representations, pages 1–13.
  39. Settles, B. (2009). Active Learning Literature Survey. Technical Report Computer Sciences Technical Report 1648, University of Wisconsin–Madison.
  40. The Next Best Underwater View. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 3764–3773, Las Vegas, NV. IEEE.
  41. Towards Adaptive Benthic Habitat Mapping. Proceedings - IEEE International Conference on Robotics and Automation, pages 9263–9270.
  42. Mastering the game of Go with deep neural networks and tree search. Nature, 529(7587):484–489.
  43. Efficient Informative Sensing using Multiple Robots. Journal of Artificial Intelligence Research, 34:707–755.
  44. Spinoccia, M. (2011). Bathymetry Grids Of South East Tasmania Shelf. Geoscience Australia, Canberra, Australia.
  45. Airborne mapping of benthic reflectance spectra with Bayesian linear mixtures. Remote Sensing of Environment, 200(August 2016):18–30.
  46. Visualizing data using t-SNE. Journal of Machine Learning Research, 9(1):2579–2605.
  47. DeepIG: Multi-robot information gathering with deep reinforcement learning. IEEE Robotics and Automation Letters, 4(3):3059–3066.
  48. Multiscale terrain analysis of multibeam bathymetry data for habitat mapping on the continental slope. Marine Geodesy, 30(1-2):3–35.
  49. Adaptive path planning for depth-constrained bathymetric mapping with an autonomous surface vessel. Journal of Field Robotics, 35(3):345–358.
  50. GeoCLR: Georeference Contrastive Learning for Efficient Seafloor Image Interpretation. Field Robotics, 2(1):1134–1155.
Citations (2)
View on Semantic Scholar

Summary

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

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