Splatblox: Traversability-Aware Gaussian Splatting for Outdoor Robot Navigation
This addresses the problem of robust robot navigation in challenging outdoor settings for robotics applications, representing a strong specific gain rather than a foundational advancement.
The paper tackled autonomous navigation in outdoor environments with dense vegetation and complex terrain by developing Splatblox, a real-time system that fuses RGB images and LiDAR using Gaussian Splatting to create a traversability-aware ESDF, resulting in over 50% higher success rate, 40% fewer freezing incidents, 5% shorter paths, and up to 13% faster time to goal in field trials.
We present Splatblox, a real-time system for autonomous navigation in outdoor environments with dense vegetation, irregular obstacles, and complex terrain. Our method fuses segmented RGB images and LiDAR point clouds using Gaussian Splatting to construct a traversability-aware Euclidean Signed Distance Field (ESDF) that jointly encodes geometry and semantics. Updated online, this field enables semantic reasoning to distinguish traversable vegetation (e.g., tall grass) from rigid obstacles (e.g., trees), while LiDAR ensures 360-degree geometric coverage for extended planning horizons. We validate Splatblox on a quadruped robot and demonstrate transfer to a wheeled platform. In field trials across vegetation-rich scenarios, it outperforms state-of-the-art methods with over 50% higher success rate, 40% fewer freezing incidents, 5% shorter paths, and up to 13% faster time to goal, while supporting long-range missions up to 100 meters. Experiment videos and more details can be found on our project page: https://splatblox.github.io