NavGSim: High-Fidelity Gaussian Splatting Simulator for Large-Scale Navigation
This work addresses a critical problem in robot learning by providing a high-fidelity simulator for large-scale navigation, though it appears incremental as it builds on existing Gaussian Splatting techniques.
The authors tackled the challenge of simulating realistic large-scale navigation environments for robots by developing NavGSim, a Gaussian Splatting-based simulator that enables photorealistic rendering across hundreds of square meters and enhances a Vision-Language-Action model's scene understanding in both simulated and real-world tests.
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.