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

Jiahang Liu; Yuanxing Duan; Jiazhao Zhang; Minghan Li; Shaoan Wang; Zhizheng Zhang; He Wang

cs.ROMar 16, 2026

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

Authors: Jiahang Liu, Yuanxing Duan, Jiazhao Zhang, Minghan Li, Shaoan Wang, Zhizheng Zhang, He Wang

Organizations: Peking University · Galbot · BAAI

Abstract

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.

Figures & tables

Fig. 2 : NavGSim’s sample code

Fig. 3 : Illustration of Gaussian Slicing for Navigable Areas . The left image shows the 3D Sofa model projected onto multiple horizontal Z-planes ( $Z_{i}$ , $Z_{i+1}$ , $Z_{i+2}$ ) at fixed height intervals. Each plane contains a 2D Gaussian slice that represents the projection of the Sofa at that particular height. These slices are combined to form a 2D collision map, with the right image showing the entire scene’s 2-D occupancy map that serves as geometric prior information for downstream tasks such as navigation cost-map construction or collision checking.

Fig. 4 : VLA-NavGSim architecture . Our VLA model takes multiple frames of images and language instructions as input. The images are processed by a Vision Encoder to extract visual features. The resulting visual tokens, along with the language tokens, are fed into the LLM to generate a predicted token. This token is then passed through a lightweight MLP to generate a trajectory.

Fig. 5 : Visualisation of reconstructed Gaussian Splatting and rendering examples. (Left) We illustrate the process of subdividing the scene into spatial chunks using H3DGS for efficient reconstruction. (Right) We compare rendering results of NavGsim with real-world image at seven distinct viewpoints (A-F).

Fig. 6 : Visualization of real-world results. Visualization First-person perspective display of real-world testing.

Fig. 7 : Real machine deployment architecture The agent interacts with the server via the Internet.

Target Category	Target	H3DGS / 3DGS
Target Category	Target	Sim SR(%) $\uparrow$	Sim DTG(m) $\downarrow$	Real SR(%) $\uparrow$
Annotated Targets	Pantry	96.7 / 83.3	0.61 / 1.75	66.7 / 0.00
	Elevator	98.3 / 83.3	0.58 / 2.73	71.4 / 16.7
	Restroom	96.7 / 86.1	1.77 / 2.10	73.3 / 23.1
	Television	100 / 91.6	0.39 / 1.28	73.3 / 18.1
	Laboratory	100 / 83.3	0.30 / 1.64	75.0 / 18.1

TABLE I : Comparison of different rendering techniques . We report navigation performance across seen and unseen targets in the simulator and real-world environments.

Method	PSNR $\uparrow$	LPIPS $\downarrow$	SSIM $\uparrow$
H3DGS	25.396	0.274	0.866
3DGS [ 12 ]	23.221	0.426	0.789

TABLE II : Comparison on different methods

Fig. 8 : Performance on NavGSim with different training strategy . Success rate comparison with and without pretraining across different training stages.

Fig. 9 : Robot Velocity vs Target Distance

Category	Avg. Trajectory Length (m)
Pantry	19.89
Elevator	26.06
Restroom	24.29
Television	18.29
Laboratory	16.80
Meeting Room I	19.43

TABLE III : Average trajectory lengths for different target categories. We report the average navigation trajectory length (in meters) across different indoor target locations.

Robotics Simulation

Robotics simulation builds virtual robots and environments to model, train, and evaluate autonomous systems before real-world deployment.

See all 320 papers

ReaDy-Go: Real-to-Sim Dynamic 3D Gaussian Splatting Simulation for Environment-Specific Visual Navigation with Moving Obstacles
Feb 12, 2026Seungyeon Yoo, Youngseok Jang, Dabin Kim +3Robotics Simulation Robot Navigation
Department of Aerospace Engineering, Seoul National University, Seoul, Republic of Korea · InnoCORE AI-Transformed Aerospace Research Center, KAIST, Daejeon, Republic of Korea
Habitat-GS: A High-Fidelity Navigation Simulator with Dynamic Gaussian Splatting
Apr 14, 2026Ziyuan Xia, Jingyi Xu, Chong Cui +9Robotics Simulation Embodied AI
Zhejiang University, Hangzhou, China · Peking University, Beijing, China · XGRIDS, Shenzhen, China +2
Image2Sim: Scaling Embodied Navigation via Generative Neural Simulator
Jul 7, 2026Zihan Wang, Seungjun Lee, Yinghao Xu +1Embodied Navigation Robotics Simulation
National University of Singapore · HKUST

Feb 12, 2026J/K move · Enter open · S save

ReaDy-Go: Real-to-Sim Dynamic 3D Gaussian Splatting Simulation for Environment-Specific Visual Navigation with Moving Obstacles

Seungyeon Yoo, Youngseok Jang, Dabin Kim, Youngsoo Han+2

Department of Aerospace Engineering, Seoul National University, Seoul, Republic of Korea · InnoCORE AI-Transformed Aerospace Research Center, KAIST, Daejeon, Republic of Korea

Robotics Simulation Robot Navigation Synthetic Data Generation for Robotics Robot Policy Generalization Dynamic Obstacle Avoidance

Open paper AskPDF arXiv

Visual navigation models often struggle in real-world dynamic environments due to limited robustness to the sim-to-real gap and the difficulty of training policies tailored to target deployment environments (e.g., households, restaurants, and factories). Although real-to-sim navigation simulation using 3D Gaussian Splatting (GS) can mitigate these challenges, prior GS-based works have considered only static scenes or non-photorealistic human obstacles built from simulator assets, despite the importance of safe navigation in dynamic environments. To address these issues, we propose ReaDy-Go, a novel real-to-sim simulation pipeline that synthesizes photorealistic dynamic scenarios in target environments by augmenting a reconstructed static GS scene with dynamic human GS obstacles, and trains navigation policies using the generated datasets. The pipeline provides three key contributions: (1) a dynamic GS simulator that integrates static scene GS with a human animation module, enabling the insertion of animatable human GS avatars and the synthesis of plausible human motions from 2D trajectories, (2) a navigation dataset generation framework that leverages the simulator along with a robot expert planner designed for dynamic GS representations and a human planner, and (3) robust navigation policies to both the sim-to-real gap and moving obstacles. The proposed simulator generates thousands of photorealistic navigation scenarios with animatable human GS avatars from arbitrary viewpoints. ReaDy-Go outperforms baselines across target environments in both simulation and real-world experiments, demonstrating improved navigation performance even after sim-to-real transfer and in the presence of moving obstacles. Moreover, zero-shot sim-to-real deployment in an unseen environment indicates its generalization potential. Project page: https://syeon-yoo.github.io/ready-go-site/.

Abstract

Robotics Simulation

Explore similar work

ReaDy-Go: Real-to-Sim Dynamic 3D Gaussian Splatting Simulation for Environment-Specific Visual Navigation with Moving Obstacles

Habitat-GS: A High-Fidelity Navigation Simulator with Dynamic Gaussian Splatting

Image2Sim: Scaling Embodied Navigation via Generative Neural Simulator