# PerSeM: Persistent Semantic Memory for Long-Horizon Open-Vocabulary UAV Mapping

arXiv: https://arxiv.org/abs/2609.19542 · HTML: https://mlsanity.com/paper/2609.19542/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 25 references that are in the map.
- First posted on arXiv 17 Sep 2026.

## Builds on (most cited first, 20 of 20)

- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [OpenScene: 3D Scene Understanding with Open Vocabularies](https://mlsanity.com/paper/2211.15654/) (2022)
- [XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model](https://mlsanity.com/paper/2207.07115/) (2022)
- [Visual Language Maps for Robot Navigation](https://mlsanity.com/paper/2210.05714/) (2022)
- [Associating Objects with Transformers for Video Object Segmentation](https://mlsanity.com/paper/2106.02638/) (2021)
- [Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation](https://mlsanity.com/paper/2106.05210/) (2021)
- [Hydra: A Real-time Spatial Perception System for 3D Scene Graph Construction and Optimization](https://mlsanity.com/paper/2201.13360/) (2022)
- [Kimera: from SLAM to Spatial Perception with 3D Dynamic Scene Graphs](https://mlsanity.com/paper/2101.06894/) (2021)
- [SemanticFusion: Dense 3D Semantic Mapping with Convolutional Neural Networks](https://mlsanity.com/paper/1609.05130/) (2016)
- [Classifying, Segmenting, and Tracking Object Instances in Video with Mask Propagation](https://mlsanity.com/paper/1912.04573/) (2019)
- [PanopticFusion: Online Volumetric Semantic Mapping at the Level of Stuff and Things](https://mlsanity.com/paper/1903.01177/) (2019)
- [Video K-Net: A Simple, Strong, and Unified Baseline for Video Segmentation](https://mlsanity.com/paper/2204.04656/) (2022)
- [Open-Fusion: Real-time Open-Vocabulary 3D Mapping and Queryable Scene Representation](https://mlsanity.com/paper/2310.03923/) (2023)
- [UAVScenes: A Multi-Modal Dataset for UAVs](https://mlsanity.com/paper/2507.22412/) (2025)
- [Open-Vocabulary Online Semantic Mapping for SLAM](https://mlsanity.com/paper/2411.15043/) (2024)
- [Vision-aided UAV navigation and dynamic obstacle avoidance using gradient-based B-spline trajectory optimization](https://mlsanity.com/paper/2209.07003/) (2022)
- [OpenVox: Real-time Instance-level Open-vocabulary Probabilistic Voxel Representation](https://mlsanity.com/paper/2502.16528/) (2025)
- [OVI-MAP:Open-Vocabulary Instance-Semantic Mapping](https://mlsanity.com/paper/2603.26541/) (2026)
- [Forest Inspection Dataset for Aerial Semantic Segmentation and Depth Estimation](https://mlsanity.com/paper/2403.06621/) (2024)
- [FUS3DMaps: Scalable and Accurate Open-Vocabulary Semantic Mapping by 3D Fusion of Voxel- and Instance-Level Layers](https://mlsanity.com/paper/2605.03669/) (2026)

## Abstract (arXiv)

Open-vocabulary segmentation enables rich semantic perception for UAVs, but frame-wise predictions can remain temporally inconsistent across repeated observations and changing viewpoints. We present PerSeM, a training-free persistent semantic memory framework for long-horizon open-vocabulary UAV mapping. PerSeM associates frame-wise semantic observations with persistent world-space voxels and constructs a majority-based semantic memory, which is conservatively refined through history-preserving spatial refinement, trust-aware replay, and context-guided verification. Experiments on the Forest and UAVScenes benchmarks show that persistent 3D memory provides substantial gains in semantic correctness and temporal stability over frame-wise predictions. Beyond this strong persistent-memory baseline, PerSeM provides consistent additional improvements, improving both semantic accuracy and temporal stability across all five evaluated UAVScenes sequences. Analysis using regions identified independently of the final PerSeM predictions further shows that these gains are concentrated in semantically difficult and temporally unstable regions, where majority-based memory is most likely to remain uncertain. These results demonstrate that persistent 3D aggregation provides a strong foundation for long-horizon semantic mapping, while conservative refinement of uncertain memory states can provide additional improvements without retraining or additional neural-network inference.