A Centerline-Aligned Frenet Graph Framework for Surface-Based Path Planning in Pipeline Environments
Hao Liu, gang liu, Chuan Qin, Yu Wang
AI summary
Problem
Existing path planning methods struggle with the curved, constrained, and geometrically complex surfaces of pipelines, often suffering from computational expense, discretization artifacts, or poor geometric consistency for climbing robots.
Approach
The method parameterizes the pipeline surface using its central axis and a Frenet coordinate system to create a structured 2D manifold grid, then uses a hybrid A* search for an initial path and quadratic programming to optimize it while respecting kinematic and adhesion constraints.
Key results
- Frenet-aligned parametric manifold reduces representation and search complexity
- Hybrid A* search generates kinematically feasible initial paths on the 2D grid
- Quadratic programming optimizes paths for smoothness, length, and energy efficiency
- Simulations and real-world tests show improved efficiency and robustness in complex pipelines
Why it matters
Enables reliable, energy-efficient autonomous navigation for magnetic wheeled inspection robots in critical infrastructure, bridging the gap between geometric accuracy and computational tractability.
Abstract
Pipeline inspection is essential for maintaining the safety of critical infrastructure, but manual inspection is dangerous and inefficient, and existing robotic solutions struggle to handle curved and constrained surfaces. Tradi- tional planning methods are either computationally expensive or prone to redundancy and discretization artifacts. To ad- dress these challenges, this paper proposes a centerline-aligned Frenet graph framework for surface-based path planning in pipeline environments. By embedding the pipeline surface into a structured two-dimensional manifold passing through the pipeline’s central axis, the framework enables efficient heuristic search while maintaining geometric consistency. By combin- ing quadratic programming with kinematic limits, an initial geodesic constrained path is generated and optimized, resulting in a smooth and executable trajectory. Extensive experiments on pipelines with sharp bends, intersections, and real-world pipeline environments demonstrate significant improvements in computational efficiency, path quality, and robustness compared to traditional methods.