NavGSim: High-Fidelity Gaussian Splatting Simulator for Large-Scale Navigation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Liu, Jiahang, Duan, Yuanxing, Zhang, Jiazhao, Li, Minghan, Wang, Shaoan, Zhang, Zhizheng, Wang, He
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911519469469696
author Liu, Jiahang
Duan, Yuanxing
Zhang, Jiazhao
Li, Minghan
Wang, Shaoan
Zhang, Zhizheng
Wang, He
author_facet Liu, Jiahang
Duan, Yuanxing
Zhang, Jiazhao
Li, Minghan
Wang, Shaoan
Zhang, Zhizheng
Wang, He
contents Simulating realistic environments for robots is widely recognized as a critical challenge in robot learning, particularly in terms of rendering and physical simulation. This challenge becomes even more pronounced in navigation tasks, where trajectories often extend across multiple rooms or entire floors. In this work, we present NavGSim, a Gaussian Splatting-based simulator designed to generate high-fidelity, large-scale navigation environments. Built upon a hierarchical 3D Gaussian Splatting framework, NavGSim enables photorealistic rendering in expansive scenes spanning hundreds of square meters. To simulate navigation collisions, we introduce a Gaussian Splatting-based slice technique that directly extracts navigable areas from reconstructed Gaussians. Additionally, for ease of use, we provide comprehensive NavGSim APIs supporting multi-GPU development, including tools for custom scene reconstruction, robot configuration, policy training, and evaluation. To evaluate NavGSim's effectiveness, we train a Vision-Language-Action (VLA) model using trajectories collected from NavGSim and assess its performance in both simulated and real-world environments. Our results demonstrate that NavGSim significantly enhances the VLA model's scene understanding, enabling the policy to handle diverse navigation queries effectively.
format Preprint
id arxiv_https___arxiv_org_abs_2603_15186
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle NavGSim: High-Fidelity Gaussian Splatting Simulator for Large-Scale Navigation
Liu, Jiahang
Duan, Yuanxing
Zhang, Jiazhao
Li, Minghan
Wang, Shaoan
Zhang, Zhizheng
Wang, He
Robotics
Simulating realistic environments for robots is widely recognized as a critical challenge in robot learning, particularly in terms of rendering and physical simulation. This challenge becomes even more pronounced in navigation tasks, where trajectories often extend across multiple rooms or entire floors. In this work, we present NavGSim, a Gaussian Splatting-based simulator designed to generate high-fidelity, large-scale navigation environments. Built upon a hierarchical 3D Gaussian Splatting framework, NavGSim enables photorealistic rendering in expansive scenes spanning hundreds of square meters. To simulate navigation collisions, we introduce a Gaussian Splatting-based slice technique that directly extracts navigable areas from reconstructed Gaussians. Additionally, for ease of use, we provide comprehensive NavGSim APIs supporting multi-GPU development, including tools for custom scene reconstruction, robot configuration, policy training, and evaluation. To evaluate NavGSim's effectiveness, we train a Vision-Language-Action (VLA) model using trajectories collected from NavGSim and assess its performance in both simulated and real-world environments. Our results demonstrate that NavGSim significantly enhances the VLA model's scene understanding, enabling the policy to handle diverse navigation queries effectively.
title NavGSim: High-Fidelity Gaussian Splatting Simulator for Large-Scale Navigation
topic Robotics
url https://arxiv.org/abs/2603.15186