We address the challenge of task-oriented navigation in unstructured and unknown environments, where robots must incrementally build and reason on rich, metric-semantic maps in real time. Since tasks may require clarification or re-specification, it is necessary for the information in the map to be rich enough to enable generalization across a wide range of tasks. To effectively execute tasks specified in natural language, we propose a hierarchical representation built on language-embedded Gaussian splatting that enables both sparse semantic planning that lends itself to online operation and dense geometric representation for collision-free navigation. We validate the effectiveness of our method through real-world robot experiments conducted in both cluttered indoor and kilometer-scale outdoor environments, with a competitive ratio of about 60% against privileged baselines. Experiment videos and more details can be found on our project page: https://atlasnav.github.io
@article{arxiv.2502.20386,
title = {ATLAS Navigator: Active Task-driven LAnguage-embedded Gaussian Splatting},
author = {Dexter Ong and Yuezhan Tao and Varun Murali and Igor Spasojevic and Vijay Kumar and Pratik Chaudhari},
journal= {arXiv preprint arXiv:2502.20386},
year = {2025}
}