Gaussian Splatting as a Unified Representation for Autonomy in Unstructured Environments

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ong, Dexter, Tao, Yuezhan, Murali, Varun, Spasojevic, Igor, Kumar, Vijay, Chaudhari, Pratik
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915291569586176
author Ong, Dexter
Tao, Yuezhan
Murali, Varun
Spasojevic, Igor
Kumar, Vijay
Chaudhari, Pratik
author_facet Ong, Dexter
Tao, Yuezhan
Murali, Varun
Spasojevic, Igor
Kumar, Vijay
Chaudhari, Pratik
contents In this work, we argue that Gaussian splatting is a suitable unified representation for autonomous robot navigation in large-scale unstructured outdoor environments. Such environments require representations that can capture complex structures while remaining computationally tractable for real-time navigation. We demonstrate that the dense geometric and photometric information provided by a Gaussian splatting representation is useful for navigation in unstructured environments. Additionally, semantic information can be embedded in the Gaussian map to enable large-scale task-driven navigation. From the lessons learned through our experiments, we highlight several challenges and opportunities arising from the use of such a representation for robot autonomy.
format Preprint
id arxiv_https___arxiv_org_abs_2505_11794
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Gaussian Splatting as a Unified Representation for Autonomy in Unstructured Environments
Ong, Dexter
Tao, Yuezhan
Murali, Varun
Spasojevic, Igor
Kumar, Vijay
Chaudhari, Pratik
Robotics
In this work, we argue that Gaussian splatting is a suitable unified representation for autonomous robot navigation in large-scale unstructured outdoor environments. Such environments require representations that can capture complex structures while remaining computationally tractable for real-time navigation. We demonstrate that the dense geometric and photometric information provided by a Gaussian splatting representation is useful for navigation in unstructured environments. Additionally, semantic information can be embedded in the Gaussian map to enable large-scale task-driven navigation. From the lessons learned through our experiments, we highlight several challenges and opportunities arising from the use of such a representation for robot autonomy.
title Gaussian Splatting as a Unified Representation for Autonomy in Unstructured Environments
topic Robotics
url https://arxiv.org/abs/2505.11794