Education, Science, Technology, Innovation and Life
Open Access
Sign In
  1. Home
  2. Journals
  3. Journal of Engineering Mechanics and Machinery
  4. Vol 11, Issue 1, 2026

Hybrid 3D Coverage Path Planning for Precision Inspection of Large-scale Underwater Structures by AUVs

Download as PDF

DOI: 10.23977/jemm.2026.110110 | Downloads: 1 | Views: 103

Author(s)

Yushen Duan 1, Yao Huang 1, Xiaolong Fan 1, Haoran Wang 1

Affiliation(s)

1 School of Mechanical Engineering, University of Shanghai for Science and Technology, Shanghai, China

Corresponding Author

Yushen Duan

ABSTRACT

To address the challenges of balancing surface conformality and obstacle avoidance during Autonomous Underwater Vehicle (AUV) inspection of deep-water SPAR platforms, this paper proposes a hybrid 3D Coverage Path Planning (CPP) method fusing improved Glasius Bio-inspired Neural Network (GBNN) guidance with local contour repair. Adopting a "global guidance plus local fine-inspection" strategy, an improved static GBNN model efficiently establishes environmental topology to locate targets with low computational cost. Subsequently, a slicing-based contour generation algorithm ensures tight wall-following coverage. To handle unmodeled obstacles like anodes, a "detection-segmentation-repair" mechanism utilizing a 26-neighbor 3D A* algorithm constructs surgical avoidance paths within minimal topological space. Simulation results indicate that in obstacle-free environments, the hybrid method reduces path length by 84% and coverage time by 91% compared to single GBNN. In complex environments, efficiency improves by 8.6% over traditional slicing methods, with a path repetition rate of only 3.74%. The results confirm the algorithm's ability to autonomously select between "horizontal bypass" and "vertical surmounting" strategies based on obstacle geometry, effectively resolving path deadlocks and ensuring complete coverage.

KEYWORDS

Autonomous Underwater Vehicle (AUV); 3D Coverage Path Planning; GBNN; Contour Scanning; 3D A* Avoidance

CITE THIS PAPER

Yushen Duan, Yao Huang, Xiaolong Fan, Haoran Wang. Hybrid 3D Coverage Path Planning for Precision Inspection of Large-scale Underwater Structures by AUVs. Journal of Engineering Mechanics and Machinery (2026). Vol. 11, No. 1, 96-111. DOI: http://dx.doi.org/10.23977/jemm.2026.110110.

REFERENCES

[1] K. P. Jayalakshmi, V. G. Nair, and D. Sathish, "A Comprehensive Survey on Coverage Path Planning for Mobile Robots in Dynamic Environments," IEEE Access, vol. 13, pp. 60185-60212, 2025.
[2] E. Galceran, R. Campos, N. Palomeras, M. Carreras, and P. Ridao, "Coverage path planning with realtime replanning for inspection of 3D underwater structures," in 2014 IEEE International Conference on Robotics and Automation (ICRA), Hong Kong, China, 2014, pp. 6586-6591.
[3] S. Jung, S. Song, P. Youn, and H. Myung, "Multi-layer Coverage Path Planner for Autonomous Structural Inspection of High-rise Structures," in IEEE/RSJ IROS, 2018.
[4] S. S. Mansouri, C. Kanellakis, E. Fresk, D. Kominiak, and G. Nikolakopoulos, "Cooperative coverage path planning for visual inspection," Control Engineering Practice, vol. 74, pp. 118-131, 2018.
[5] I. Z. Biundini, M. F. Pinto, A. G. Melo, et al., "A Framework for Coverage Path Planning Optimization Based on Point Cloud for Structural Inspection," Sensors, vol. 21, no. 2, p. 570, 2021.
[6] Y. S. Song and M. R. Arshad, "Path planning for an autonomous underwater vehicle in pole inspection," Indian Journal of Geo-Marine Sciences, vol. 47, no. 12, pp. 2477-2484, 2018.
[7] N. Palomeras, N. Hurtós, M. Carreras, and P. Ridao, "Autonomous Mapping of Underwater 3-D Structures: From View Planning To Execution," IEEE Robotics and Automation Letters, vol. 3, no. 3, pp. 1965-1972, 2018.
[8] S. Song and S. Jo, "Surface-based Exploration for Autonomous 3D Modeling," in IEEE ICRA, 2018.
[9] R. Almadhoun, T. Taha, D. Gan, et al., "Coverage Path Planning with Adaptive Viewpoint Sampling to Construct 3D Models of Complex Structures," in IEEE/RSJ IROS, 2018.
[10] W. Jing, D. Deng, Z. Xiao, et al., "Coverage Path Planning using Path Primitive Sampling and Primitive Coverage Graph for Visual Inspection," in IEEE/RSJ IROS, 2019.
[11] C. Cao, J. Zhang, M. Travers, and H. Choset, "Hierarchical Coverage Path Planning in Complex 3D Environments," in IEEE ICRA, 2020.
[12] N. Karapetyan, J. V. Johnson, and I. Rekleitis, "Coverage Path Planning for Mapping of Underwater Structures," in IEEE OCEANS, 2020.
[13] G. Han, Y. Hou, W. Lai, et al., "A Multi-Dimensional Optimization Framework for AUV Cooperative Coverage Path Planning in Dynamic Underwater Environments," IEEE Transactions on Vehicular Technology, vol. 74, no. 11, 2025.
[14] C. Su, Y. Li, H. Wang, and G. Wan, "3D Coverage Path Planning for Underwater Dam Inspection Based on WaveOptima," Information and Control, vol. 53, 2024.
[15] Z. Shang, J. Bradley, and Z. Shen, "A co-optimal coverage path planning method for aerial scanning of complex structures," Expert Systems with Applications, vol. 158, p. 113535, 2020.
[16] Z. Shen, "3-D Coverage Path Planning for Underwater Terrain Mapping," Master's thesis, University of Connecticut, 2017.
[17] Z. Shen, J. Song, K. Mittal, and S. Gupta, "CT-CPP: Coverage Path Planning for 3D Terrain Reconstruction Using Dynamic Coverage Trees," IEEE Robotics and Automation Letters, vol. 7, no. 1, pp. 135-142, 2022.
[18] L. Zhou, Z. Deng, G. Bai, et al., "A real time data-driven dynamic glasius bionic neural network path planning algorithm for polar under-ice feature scanning," Ocean Engineering, vol. 312, p. 119289, 2024.
[19] W. Cai, S. Zhang, M. Zhang, and C. Wang, "Improved BINN-Based Underwater Topography Scanning Coverage Path Planning for AUV in Internet of Underwater Things," IEEE Internet of Things Journal, vol. 10, no. 20, pp. 18375-18386, 2023.
[20] S. Song, D. Kim, and S. Jo, "Online coverage and inspection planning for 3D modeling," Autonomous Robots, vol. 44, pp. 1431-1450, 2020.

All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.