用高斯点云构建大场景导航模拟器，提升机器人训练真实感
NavGSim: High-Fidelity Gaussian Splatting Simulator for Large-Scale Navigation
- 基于分层高斯点云生成百平米级逼真环境
- 直接从点云提取可通行区域，支持碰撞检测
- 提供多GPU工具链，适合训练视觉语言导航模型
为机器人学习构建逼真环境是关键挑战，尤其在跨房间或整层楼的导航任务中更为突出。本文提出NavGSim，一种基于高斯点云的模拟器，可生成百平米级的大规模高保真导航环境。基于分层3D高斯点云框架，该模拟器实现大场景下的照片级渲染。为支持导航碰撞模拟，提出一种基于高斯点云的切片技术，直接从重建的高斯点云中提取可通行区域。为便于使用，提供完整的NavGSim API，支持多GPU开发，包含自定义场景重建、机器人配置、策略训练与评估工具。通过在NavGSim上收集轨迹训练视觉-语言-动作（VLA）模型，并在仿真和真实环境中评估其性能，结果表明NavGSim显著提升了模型对场景的理解能力，使其能有效应对多样化的导航指令。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。