GRAND-SLAM: Local Optimization for Globally Consistent Large-Scale Multi-Agent Gaussian SLAM
This enables rapid exploration and reconstruction of large outdoor environments using multiple robots, addressing a scalability gap in multi-agent Gaussian SLAM.
The paper tackles the problem of applying 3D Gaussian splatting to large-scale, multi-agent outdoor SLAM, which was previously limited to small-scale indoor environments, and achieves state-of-the-art tracking performance with 28% higher PSNR on indoor data and 91% lower multi-agent tracking error on outdoor data.
3D Gaussian splatting has emerged as an expressive scene representation for RGB-D visual SLAM, but its application to large-scale, multi-agent outdoor environments remains unexplored. Multi-agent Gaussian SLAM is a promising approach to rapid exploration and reconstruction of environments, offering scalable environment representations, but existing approaches are limited to small-scale, indoor environments. To that end, we propose Gaussian Reconstruction via Multi-Agent Dense SLAM, or GRAND-SLAM, a collaborative Gaussian splatting SLAM method that integrates i) an implicit tracking module based on local optimization over submaps and ii) an approach to inter- and intra-robot loop closure integrated into a pose-graph optimization framework. Experiments show that GRAND-SLAM provides state-of-the-art tracking performance and 28% higher PSNR than existing methods on the Replica indoor dataset, as well as 91% lower multi-agent tracking error and improved rendering over existing multi-agent methods on the large-scale, outdoor Kimera-Multi dataset.