Constraint Manifold Exploration for Efficient Continuous Coverage Estimation
Robert Wilbrandt, Rüdiger Dillmann
AI summary
Problem
Industrial robots require full surface coverage while maintaining strict tool orientation constraints, but existing methods lack accurate feasibility analysis for continuous coverage. Prior approaches rely on surface discretization or fail to guarantee constraint adherence, leading to unreliable coverage estimates.
Approach
The authors construct an implicit constraint manifold in an extended configuration space to exactly represent tool position and orientation constraints. They explore this manifold using two sampling strategies: a uniform RRT baseline and a biased KPIECE-inspired method that directs exploration toward unexplored surface regions.
Key results
- Biased sampling achieves superior runtime and sample efficiency over uniform RRT in complex scenarios
- Accurately estimates continuous coverage without underestimating reachable regions near obstacles
- Identifies optimal sampling parameters balancing coverage accuracy and computational cost
- Validated across 6-DOF and 7-DOF robots on high-curvature surfaces and maze-like environments
Why it matters
Provides manufacturing engineers with a reliable tool to verify coverage feasibility before deployment, preventing costly planning failures in automated surface finishing and inspection.
Abstract
Many automated manufacturing processes rely on industrial robot arms to move process-specific tools along workpiece surfaces. In applications like grinding, sanding, spray painting, or inspection, they need to cover a workpiece fully while keeping their tools perpendicular to its surface. While there are approaches to generate trajectories for these applications, there are no sufficient methods for analyzing the feasibility of full surface coverage. This work proposes a sampling-based approach for continuous coverage estimation that explores reachable surface regions in the configuration space. We define an extended ambient configuration space that allows for the representation of tool position and orientation constraints. A continuation-based approach is used to explore it using two different sampling strategies. A thorough evaluation across different kinematics and environments analyzes their runtime and efficiency. This validates our ability to accurately and efficiently calculate surface coverage for complex surfaces in complicated environments.