GGraph speeds up robot path planning with GPU graph processing
GGraph: A GPU-Accelerated Library for Graph-Based Robot Deployment and Learning
Robotics
Summary
Autonomous robots need maps that show where to go and what things are, but those maps must be simple enough for quick planning. The authors found that existing tools for building these maps run too slowly on CPUs, especially when training many robots at once. They created GGraph, a new library that uses graphics cards (GPUs) to build and update these maps much faster. This tool works both on real robots and in large-scale training programs, cutting training time significantly.
What this means in practice
- •For robotics development teams: Train hundreds of robot navigation policies simultaneously by using GPU-accelerated graph updates to reduce training times by a factor of ten.
- •For robot software engineers: Deploy real-time graph-based navigation and exploration algorithms on robots using fast GPU-backed graph updates integrated with ROS 2.
Authors
Yash Rampuria, Rohan Garg, Daniele Gammelli, Marco Pavone
Abstract
Autonomous mobile robots require spatial representations that capture geometry and semantics while staying sparse enough for planning in large, unknown environments. Graphs provide a natural representation for this purpose and underpin both classical planning methods and a growing class of reinforcement-learning (RL) policies. However, RL training needs hundreds to thousands of parallel environments, each constructing and updating its own graph. Existing graph libraries are typically designed for either single-robot deployment or fixed graphs, and CPU-based graph construction limits scalable training to only a few dozen environments. We introduce GGraph, an open-source GPU-accelerated graph library for both robot deployment and large-scale learning. GGraph supports real robots through ROS 2 interfaces and vectorized GPU-based policy training, with built-in support for tasks including 3-D navigation, exploration, and loop-closure integration. For single-robot operation, GGraph updates graphs in milliseconds. At scale, it enables graph-based exploration policies to train across hundreds of parallel robots, reducing wall-clock training time by one order of magnitude. Across simulation and real-world experiments, these results establish GGraph as a unified graph infrastructure for both large-scale robot learning and deployment.