# ActiveLang: Active Open-Vocabulary 3D Mapping with Semantic-Uncertainty-Guided Exploration

arXiv: https://arxiv.org/abs/2610.09518 · HTML: https://mlsanity.com/paper/2610.09518/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 70 references that are in the map.
- First posted on arXiv 7 Oct 2026.

## Builds on (most cited first, 10 of 10)

- [The Replica Dataset: A Digital Replica of Indoor Spaces](https://mlsanity.com/paper/1906.05797/) (2019)
- [SemGauss-SLAM: Dense Semantic Gaussian Splatting SLAM](https://mlsanity.com/paper/2403.07494/) (2024)
- [ActiveRMAP: Radiance Field for Active Mapping And Planning](https://mlsanity.com/paper/2211.12656/) (2022)
- [Active Implicit Object Reconstruction using Uncertainty-guided Next-Best-View Optimization](https://mlsanity.com/paper/2303.16739/) (2023)
- [Neural Implicit Dense Semantic SLAM](https://mlsanity.com/paper/2304.14560/) (2023)
- [Semantic Mapping in Indoor Embodied AI -- A Survey on Advances, Challenges, and Future Directions](https://mlsanity.com/paper/2501.05750/) (2025)
- [Semantically-aware Neural Radiance Fields for Visual Scene Understanding: A Comprehensive Review](https://mlsanity.com/paper/2402.11141/) (2024)
- [Multimodal LLM Guided Exploration and Active Mapping using Fisher Information](https://mlsanity.com/paper/2410.17422/) (2024)
- [OpenMonoGS-SLAM: Monocular Gaussian Splatting SLAM with Open-set Semantics](https://mlsanity.com/paper/2512.08625/) (2025)
- [RoboAtlas: Contextual Active SLAM](https://mlsanity.com/paper/2606.26046/) (2026)

## Abstract (arXiv)

As robots increasingly assist humans with diverse tasks, they need both geometric and semantic understanding of their surroundings. Moreover, robots often operate in unfamiliar environments and take on new tasks without knowing the relevant concepts ahead of time. This motivates language-annotated 3D maps that support open-vocabulary scene understanding and human-robot interaction. We introduce ActiveLang, an autonomous system for active open-vocabulary 3D mapping with semantic-uncertainty-guided exploration. ActiveLang performs online language-feature adaptation on a compact dual-Gaussian representation to jointly reconstruct scene geometry, appearance, and open-vocabulary semantics with modest memory overhead. Its planner efficiently selects informative viewpoints, enabling effective mapping with fewer observations and lower computational cost. Experiments on Replica and ScanNet++ demonstrate substantial improvements in 2D and 3D open-vocabulary segmentation over both online and offline baselines, highlighting that actively exploring scenes builds language-annotated 3D maps more efficiently.