Metraipolis › archive › dc_eaa3d452079d
PerSeM: Persistent Semantic Memory for Long-Horizon Open-Vocabulary UAV Mapping — arXiv:2609.19542
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.19542
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-10T05:05:25.645Z
- SHA-256 of the archived text
f1f82b5378051fc711abcaaf56a2066fe8e0b6c78cbb062faed7603948b1bcea- Stable URL of this page
https://metraipolis.com/documento/dc_eaa3d452079d
How to cite
PerSeM: Persistent Semantic Memory for Long-Horizon Open-Vocabulary UAV Mapping — arXiv:2609.19542 — arXiv (en), https://arxiv.org/abs/2609.19542 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_eaa3d452079d (Metraipolis archive dc_eaa3d452079d, sha256 f1f82b5378051fc711abcaaf56a2066fe8e0b6c78cbb062faed7603948b1bcea)
BibTeX
@misc{dceaa3d452079d,
title = {PerSeM: Persistent Semantic Memory for Long-Horizon Open-Vocabulary UAV Mapping — arXiv:2609.19542},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.19542},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_eaa3d452079d; sha256 f1f82b5378051fc711abcaaf56a2066fe8e0b6c78cbb062faed7603948b1bcea},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.19542. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-18 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2609.19542 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-10T04:26:09.512Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).