RT-GuIDE: Real-Time Gaussian Splatting for Information-Driven Exploration

TL;DR

This paper introduces RT-GuIDE, a real-time Gaussian splatting framework for active mapping and exploration, enabling fast, high-quality dense maps for autonomous navigation and semantic segmentation.

Contribution

It develops a GPU-accelerated motion planning algorithm that constructs optimized Gaussian maps for real-time, high-quality mapping and exploration, outperforming existing methods in speed and accuracy.

Findings

Achieves comparable PSNR to state-of-the-art while being much faster.

Improves map quality with at least 0.8dB higher PSNR and 16% better geometric accuracy.

Enables effective semantic segmentation using off-the-shelf models.

Abstract

We propose a framework for active mapping and exploration that leverages Gaussian splatting for constructing dense maps. Further, we develop a GPU-accelerated motion planning algorithm that can exploit the Gaussian map for real-time navigation. The Gaussian map constructed onboard the robot is optimized for both photometric and geometric quality while enabling real-time situational awareness for autonomy. We show through viewpoint selection experiments that our method yields comparable Peak Signal-to-Noise Ratio (PSNR) and similar reconstruction error to state-of-the-art approaches, while being orders of magnitude faster to compute. In closed-loop physics-based simulation and real-world experiments, our algorithm achieves better map quality (at least 0.8dB higher PSNR and more than 16% higher geometric reconstruction accuracy) than maps constructed by a state-of-the-art method, enabling semantic segmentation using off-the-shelf open-set models. Experiment videos and more details can be found on our project page: https://tyuezhan.github.io/RT GuIDE/