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

Yuezhan Tao, Dexter Ong, Varun Murali, Igor Spasojevic, Pratik Chaudhari, Vijay Kumar,
The GRASP Lab, University of Pennsylvania
arXiv Video

Abstract

We propose a framework for active mapping and exploration that leverages Gaussian splatting for constructing information-rich maps. Further, we develop a parallelized mo- tion 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 qual- ity while enabling real-time situational awareness for autonomy. We show through simulation experiments that our method is competitive with approaches that use alternate information gain metrics, while being orders of magnitude faster to compute. In real-world experiments, our algorithm achieves better map quality (10% higher Peak Signal-to-Noise Ratio (PSNR) and 30% higher geometric reconstruction accuracy) than Gaussian maps constructed by traditional exploration baselines.

Video

Offline reconstruction from our experiments.

System Overview

system diagram

The proposed framework contains two major components, the planning module and the mapping module. As can be seen in the figure, the Mapping module ([A]) takes in RGB, depth and pose measurements, and updates the map representation m at every step and computes the utility of geometrically clustered frontiers. The information is then passed to the planning module which comprises the topological graph and motion primitive library ([B]). The topological graph adds sampled viewpoints as nodes and passes along a planned path to the trajectory planner. The trajectory planner in turn attempts to plan a path to goal that maximizes information gathering (queried from the mapper). The planned trajectory is executed by the robot to get a new set of observations.

BibTeX

@misc{tao2024rtguiderealtimegaussiansplatting,
      title={RT-GuIDE: Real-Time Gaussian splatting for Information-Driven Exploration}, 
      author={Yuezhan Tao and Dexter Ong and Varun Murali and Igor Spasojevic and Pratik Chaudhari and Vijay Kumar},
      year={2024},
      eprint={2409.18122},
      archivePrefix={arXiv},
      primaryClass={cs.RO},
      url={https://arxiv.org/abs/2409.18122}, 
}