PierGuard: A Planning Framework for Underwater Robotic Inspection of Coastal Piers

TL;DR

PierGuard addresses the challenge of fast, reliable global path planning for underwater pier inspection by fusing bidirectional sampling with a neural network that outputs high-quality heuristic regions. The approach introduces a dedicated neural architecture that processes dual 3D grids to produce a heuristic region, guided by a loss formulation that emphasizes both local path accuracy and global shape, and it guarantees probabilistic completeness and asymptotic optimality. Empirical results from simulations and real-world field tests show substantial improvements over both geometric and learning-based baselines, including faster convergence and better robustness in cluttered underwater environments. The framework enables scalable, automated pier inspections with potential to enhance maritime safety and maintenance operations.

Abstract

Using underwater robots instead of humans for the inspection of coastal piers can enhance efficiency while reducing risks. A key challenge in performing these tasks lies in achieving efficient and rapid path planning within complex environments. Sampling-based path planning methods, such as Rapidly-exploring Random Tree* (RRT*), have demonstrated notable performance in high-dimensional spaces. In recent years, researchers have begun designing various geometry-inspired heuristics and neural network-driven heuristics to further enhance the effectiveness of RRT*. However, the performance of these general path planning methods still requires improvement when applied to highly cluttered underwater environments. In this paper, we propose PierGuard, which combines the strengths of bidirectional search and neural network-driven heuristic regions. We design a specialized neural network to generate high-quality heuristic regions in cluttered maps, thereby improving the performance of the path planning. Through extensive simulation and real-world ocean field experiments, we demonstrate the effectiveness and efficiency of our proposed method compared with previous research. Our method achieves approximately 2.6 times the performance of the state-of-the-art geometric-based sampling method and nearly 4.9 times that of the state-of-the-art learning-based sampling method. Our results provide valuable insights for the automation of pier inspection and the enhancement of maritime safety. The updated experimental video is available in the supplementary materials.

Figures (14)

• Figure 1: Illustration of pier inspection: manual vs. robotic.
• Figure 2: An overview of the proposed PierGuard framework.
• Figure 3: Visualization of RRT* and our method on map 1.
• Figure 4: Visualization of RRT* and our method on map 2.
• Figure 5: Physical model-based simulation experiments.

Theorems & Definitions (3)

• proof
• proof
• proof