2DGS-Planner: Rasterization-based Path Planning in 2D Gaussian Splatting Map
2DGS-Planner: Rasterization-based Path Planning in 2D Gaussian Splatting Map
The paper presents 2DGS-Planner, a path planner for ground robots that reads planning-relevant geometry from a 2D Gaussian splatting map through rasterization. The method improves roadmap connectivity, clearance estimation, and planning success compared to baselines, demonstrating the effectiveness of rasterization as a geometric query interface for planning on Gaussian maps.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- code: Available Artifact link Open source S5
- dataset: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
e tested baselines. These results support rasterization as an effective geometric query interface for planning directly on Gaussian maps. Code and data are available at https://2dgs-planner.github.io/
Open source S5
Source：arXiv Robotics — research abstracts · arxiv.org