Metraipolis › archive › dc_2a5fc0c8fc57

ExcavaTwin: Training-Free Geometry-Guided Semantic Elevation Mapping for Autonomous Excavation — arXiv:2609.34719

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.34719
License (as archived): CC0-1.0
Archived: 2026-10-08T00:17:28.551Z
SHA-256 of the archived text: b73388f4fc1400fe874e62322d877604f59a45aa41d209149903edc3835cc315
Stable URL of this page: https://metraipolis.com/documento/dc_2a5fc0c8fc57

How to cite

ExcavaTwin: Training-Free Geometry-Guided Semantic Elevation Mapping for Autonomous Excavation — arXiv:2609.34719 — arXiv (en), https://arxiv.org/abs/2609.34719 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2a5fc0c8fc57 (Metraipolis archive dc_2a5fc0c8fc57, sha256 b73388f4fc1400fe874e62322d877604f59a45aa41d209149903edc3835cc315)

BibTeX

@misc{dc2a5fc0c8fc57,
  title = {ExcavaTwin: Training-Free Geometry-Guided Semantic Elevation Mapping for Autonomous Excavation — arXiv:2609.34719},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.34719},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2a5fc0c8fc57; sha256 b73388f4fc1400fe874e62322d877604f59a45aa41d209149903edc3835cc315},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34719. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Autonomous excavation requires a spatial representation that jointly captures terrain geometry and task-relevant semantics. Existing excavation mapping is largely elevation-centric, while generic semantic models remain unstable in unstructured outdoor scenes. We present ExcavaTwin, a pure-vision geometry-guided semantic elevation mapping framework without excavation-specific training. Given multi-view RGB images, the framework: 1) reconstructs scene geometry and semantic observations using frozen vision models; 2) derives terrain and non-terrain geometric support; 3) performs geometry-constrained multi-view semantic fusion to suppress implausible predictions and recover incomplete observations; and 4) projects the fused state into a task-oriented semantic elevation map. Experiments on public datasets and real excavation scenes demonstrate reliable geometric and semantic perception. In real excavation, the system achieved an average update interval of approximately 1.4 s and a mean elevation error of 12.74cm in dynamically modified regions. Larger errors mainly occur during rapid terrain changes and transient visual disturbances caused by machine motion.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-29 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.34719 — 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 2026-10-07T23:52:16.575Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).