analiza aiqbench
2DGS-Planner advances robot navigation by leveraging 2D Gaussian Splatting maps as a rasterizable scene representation, addressing limitations in obstacle detection inherent to individual primitive optimization. The method introduces a novel geometric query interface using orthographic and cylindrical projections to estimate clearance fields, significantly improving roadmap connectivity and planning success rates for ground robots. This work establishes a robust framework for integrating neural rendering techniques directly into motion planning pipelines without relying on traditional 3D mesh reconstruction.
2DGS-Planner: Rasterization-based Path Planning in 2D Gaussian Splatting Map
arXiv:2610.11752v1 Announce Type: new Abstract: Gaussian splatting provides an explicit and efficiently rasterizable scene representation for robot navigation. However, individual Gaussian primitives may not reliably represent obstacles as they are jointly optimized through alpha-composited rendering from a finite set of reconstruction views. We propose 2DGS-Planner, a path planner for ground robots that reads planning-relevant geometry from a 2D Gaussian splatting (2DGS) map through rasterization, rather than treating individual Gaussian primitives as obstacles. During offline roadmap construction, multi-view attribution converts rendered normal dispersion into structural scores for non-ground disks supported by the reconstruction views. These scores guide adaptive node sampling on the ground. Path-aligned orthographic queries validate candidate edges, while cylindrical queries estimate local clearance fields that are cached on the edges. During online planning, graph search initializes a route, and path refinement reuses the cached fields while accounting for the robot's dimensions and ground constraints. Experiments demonstrate improved roadmap connectivity, more accurate clearance estimation, and higher planning success compared with the 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/
Abstract:Gaussian splatting provides an explicit and efficiently rasterizable scene representation for robot navigation. However, individual Gaussian primitives may not reliably represent obstacles as they are jointly optimized through alpha-composited rendering from a finite set of reconstruction views. We propose 2DGS-Planner, a path planner for ground robots that reads planning-relevant geometry from a 2D Gaussian splatting (2DGS) map through rasterization, rather than treating individual Gaussian primitives as obstacles. During offline roadmap construction, multi-view attribution converts rendered normal dispersion into structural scores for non-ground disks supported by the reconstruction views. These scores guide adaptive node sampling on the ground. Path-aligned orthographic queries validate candidate edges, while cylindrical queries estimate local clearance fields that are cached on the edges. During online planning, graph search initializes a route, and path refinement reuses the cached fields while accounting for the robot's dimensions and ground constraints. Experiments demonstrate improved roadmap connectivity, more accurate clearance estimation, and higher planning success compared with the tested baselines. These results support rasterization as an effective geometric query interface for planning directly on Gaussian maps. Code and data are available at this https URL
Robotics (cs.RO)
arXiv:2610.11752 [cs.RO]
(or arXiv:2610.11752v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2610.11752 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 276 cuvinte
Subiecte conexe
AirSplan: Risk-Aware Motion Planning for Quadrotors in Cluttered 3D Gaussian Splats
arXiv · 21 sept. 2026
DIFF-IPPO: Diffusion-Based Informative Path Planning with Open-Vocabulary Belief Maps
arXiv · 16 iun. 2026
Path Planning with Motion Primitives in Dynamic Environments: SIPP on Lattices
arXiv · 29 sept. 2026
Calibrated Uncertainty for Informative Path Planning in Aquatic Environmental Monitoring
arXiv · 29 sept. 2026