A coverage motion planning approach for UVMS-based propeller cleaning in obstacle-occluded environments
Raksi Kopo, Spyridon Tarantos, Fotis Panetsos, Kostas Kyriakopoulos
AI summary
Problem
Prior approaches ignore the connectivity of the robot's Surface-Constrained Configuration Space, leading to unnecessary tool lift-offs and poor path quality when obstacles fragment the workspace. This work addresses how to efficiently plan whole-body UVMS trajectories that cover all propeller blades while minimizing lift-offs and respecting kinematic and collision constraints.
Approach
The method extends a hierarchical Generalized Traveling Salesman Problem framework by integrating collision-aware inverse kinematics sampling, isoline-based coverage pattern promotion, and time-optimized spline parametrization to guide search and minimize tool lift-offs without exhaustive path evaluation.
Key results
- Collision-aware hierarchical GTSP framework for disconnected configuration spaces
- Isoline-based sampling that promotes smooth coverage patterns with fewer turns
- Piecewise-linear and RRT-Connect edge costs that minimize necessary tool lift-offs
- Time-parameterized whole-body UVMS trajectory respecting velocity and acceleration limits
Why it matters
Enables safer, more efficient automated marine propeller maintenance by reducing surface damage risks and operational downtime, advancing underwater robotics for harsh environments.
Abstract
This work addresses the problem of underwater propeller cleaning in environments containing obstacles using an Underwater Vehicle Manipulator System (UVMS). Prior propeller-cleaning approaches plan coverage tool paths with- out explicitly considering the connectivity of the associated Surface-Constrained Configuration Space (SCCS), leading to unnecessary lift-offs in obstacle-occluded settings. In contrast, we formulate the coverage problem in the disconnected SCCS as a Generalized Traveling Salesman Problem (GTSP) within a hierarchical framework, accounting for obstacles and at- tempting to minimize the number of tool lift-offs. We consider explicitly the tool lift-off paths in the GTSP cost formulation, utilizing the hierarchical framework to guide the search without exhaustively evaluating all possible paths. To achieve smoother tool paths with fewer turns, we introduce a cost that promotes alignment with desired coverage curves. Finally, we time- parameterize the coverage path into a whole-body UVMS tra- jectory by minimizing the duration of the cleaning task, while respecting the robot hardware limitations. The effectiveness of the proposed method is demonstrated in a realistic simulation scenario.