紧凑化关键帧优化多智能体高斯点云SLAM
Compact Keyframe-Optimized Multi-Agent Gaussian Splatting SLAM
AI总结：
本文提出一种改进的多智能体RGB-D高斯点云SLAM框架，通过压缩步骤和中央闭环计算减少通信负载，提升地图保真度，实验证明数据传输量减少85-95%。
摘要：
高效的多智能体3D地图构建对在未知环境中运作的机器人团队至关重要，但密集表示阻碍了在受限通信链路上的实时交换。在多智能体同步定位与建图（SLAM）中，系统通常依赖集中式服务器合并和优化各个智能体生成的局部地图。然而，分享这些大地图表示，特别是由最近方法如高斯点云生成的，成为现实场景中带宽有限时的瓶颈。我们提出了一种改进的多智能体RGB-D高斯点云SLAM框架，减少通信负载的同时保持地图保真度。首先，我们将在SLAM系统中加入压缩步骤以移除冗余的3D高斯点，而不影响渲染质量。其次，我们的方法进行集中式闭环计算，无需初始猜测，以两种模式运行：纯渲染深度模式，仅需3D高斯点即可；以及相机深度模式，包含轻量级深度图像以提高配准精度和额外的高斯点修剪。在合成和现实数据集上的评估显示，与最先进方法相比，数据传输量减少了85-95%，使3D高斯多智能体SLAM更接近现实场景中的实际部署。代码：https://github.com/lemonci/coko-slam
英文摘要：
Efficient multi-agent 3D mapping is essential for robotic teams operating in unknown environments, but dense representations hinder real-time exchange over constrained communication links. In multi-agent Simultaneous Localization and Mapping (SLAM), systems typically rely on a centralized server to merge and optimize the local maps produced by individual agents. However, sharing these large map representations, particularly those generated by recent methods such as Gaussian Splatting, becomes a bottleneck in real-world scenarios with limited bandwidth. We present an improved multi-agent RGB-D Gaussian Splatting SLAM framework that reduces communication load while preserving map fidelity. First, we incorporate a compaction step into our SLAM system to remove redundant 3D Gaussians, without degrading the rendering quality. Second, our approach performs centralized loop closure computation without initial guess, operating in two modes: a pure rendered-depth mode that requires no data beyond the 3D Gaussians, and a camera-depth mode that includes lightweight depth images for improved registration accuracy and additional Gaussian pruning. Evaluation on both synthetic and real-world datasets shows up to 85-95\% reduction in transmitted data compared to state-of-the-art approaches in both modes, bringing 3D Gaussian multi-agent SLAM closer to practical deployment in real-world scenarios. Code: https://github.com/lemonci/coko-slam
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
