Multi-robot autonomous 3D reconstruction using Gaussian splatting with Semantic guidance

TL;DR

This paper introduces a multi-robot 3D scene reconstruction framework that combines Gaussian splatting with semantic guidance, enabling efficient and high-quality large-scale scene reconstruction.

Contribution

It presents the first multi-robot 3D reconstruction method based on Gaussian splatting with semantic guidance, improving speed and quality over existing single-robot approaches.

Findings

Achieves highest reconstruction quality among planning methods.

Demonstrates superior planning efficiency compared to existing multi-robot methods.

Effectively plans view paths for high-quality scene reconstruction.

Abstract

Implicit neural representations and 3D Gaussian splatting (3DGS) have shown great potential for scene reconstruction. Recent studies have expanded their applications in autonomous reconstruction through task assignment methods. However, these methods are mainly limited to single robot, and rapid reconstruction of large-scale scenes remains challenging. Additionally, task-driven planning based on surface uncertainty is prone to being trapped in local optima. To this end, we propose the first 3DGS-based centralized multi-robot autonomous 3D reconstruction framework. To further reduce time cost of task generation and improve reconstruction quality, we integrate online open-vocabulary semantic segmentation with surface uncertainty of 3DGS, focusing view sampling on regions with high instance uncertainty. Finally, we develop a multi-robot collaboration strategy with mode and task assignments improving reconstruction quality while ensuring planning efficiency. Our method demonstrates the highest reconstruction quality among all planning methods and superior planning efficiency compared to existing multi-robot methods. We deploy our method on multiple robots, and results show that it can effectively plan view paths and reconstruct scenes with high quality.