让机器人长期在动态环境里实时更新3D地图，比传统方法更快更准。
GS-LTS: 3D Gaussian Splatting-Based Adaptive Modeling for Long-Term Service Robots
- 用单图检测变化，自动收集多视角数据并编辑高斯点云更新场景。
- 在真实场景中实现1.5倍于基线的更新速度和更高重建质量。
- 专为服务机器人设计，适合长期运行的智能导航与任务执行。
3D Gaussian Splatting（3DGS）因其显式、高保真的稠密场景表征，在机器人领域受到广泛关注，展现出强大的应用潜力。然而，现有基于3DGS的机器人方法主要聚焦静态场景，对长期服务机器人所需的动态场景变化关注不足。这类机器人需持续执行任务并高效更新环境信息，而现有方法难以满足。为此，本文提出GS-LTS（Gaussian Splatting for Long-Term Service），一种基于3DGS的系统，使室内机器人能够在动态环境中长期执行多样化任务。GS-LTS通过单图像变化检测识别场景变更（如物体增减），采用规则策略自主采集多视角观测，并通过高斯编辑高效更新场景表示。此外，我们提出一个基于仿真的基准，以紧凑配置脚本自动生成场景变化数据，提供标准化、易用的评估体系。实验表明，GS-LTS在重建、导航及场景更新方面均优于基线方法——更新速度更快、质量更高，推动了3DGS在长期机器人任务中的应用。代码与基准已开源：https://vipl-vsu.github.io/3DGS-LTS。
原文摘要 · Abstract (English)
3D Gaussian Splatting (3DGS) has garnered significant attention in robotics for its explicit, high fidelity dense scene representation, demonstrating strong potential for robotic applications. However, 3DGS-based methods in robotics primarily focus on static scenes, with limited attention to the dynamic scene changes essential for long-term service robots. These robots demand sustained task execution and efficient scene updates-challenges current approaches fail to meet. To address these limitations, we propose GS-LTS (Gaussian Splatting for Long-Term Service), a 3DGS-based system enabling indoor robots to manage diverse tasks in dynamic environments over time. GS-LTS detects scene changes (e.g., object addition or removal) via single-image change detection, employs a rule-based policy to autonomously collect multi-view observations, and efficiently updates the scene representation through Gaussian editing. Additionally, we propose a simulation-based benchmark that automatically generates scene change data as compact configuration scripts, providing a standardized, user-friendly evaluation benchmark. Experimental results demonstrate GS-LTS's advantages in reconstruction, navigation, and superior scene updates-faster and higher quality than the image training baseline-advancing 3DGS for long-term robotic operations. Code and benchmark are available at: https://vipl-vsu.github.io/3DGS-LTS.
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。