Serialized Red-Green-Gray: Quicker Heuristic Validation of Edges in Dynamic Roadmap Graphs

TL;DR

The paper introduces SerRGG, a GPU-accelerated framework for rapid edge validation in dynamic roadmaps, significantly speeding up motion planning in changing environments.

Contribution

It presents the Red-Green-Gray framework and a serial GPU-accelerated variant, enabling faster heuristic validation of roadmap edges in dynamic settings.

Findings

SerRGG achieves 2-9x speedup over sequential implementation.

RGG reduces the number of edges needing full validation.

SerRGG is effective for time-critical robotic applications.

Abstract

Motion planning in dynamic environments, such as robotic warehouses, requires fast adaptation to frequent changes in obstacle poses. Traditional roadmap-based methods struggle in such settings, relying on inefficient reconstruction of a roadmap or expensive collision detection to update the existing roadmap. To address these challenges we introduce the Red-Green-Gray (RGG) framework, a method that builds on SPITE to quickly classify roadmap edges as invalid (red), valid (green), or uncertain (gray) using conservative geometric approximations. Serial RGG provides a high-performance variant leveraging batch serialization and vectorization to enable efficient GPU acceleration. Empirical results demonstrate that while RGG effectively reduces the number of unknown edges requiring full validation, SerRGG achieves a 2-9x speedup compared to the sequential implementation. This combination of geometric precision and computational speed makes SerRGG highly effective for time-critical robotic applications.