Metraipolis › archive › dc_ead76be2bed0

Masked Generative Motion Planning with Geometry-Guided Token Search — arXiv:2610.10646

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.10646
License (as archived): CC0-1.0
Archived: 2026-10-09T05:53:52.657Z
SHA-256 of the archived text: 72ed1e93468278efb61c4b71bef2d7b4d8d1c8da7c2d30644cb7c260069b693c
Stable URL of this page: https://metraipolis.com/documento/dc_ead76be2bed0

How to cite

Masked Generative Motion Planning with Geometry-Guided Token Search — arXiv:2610.10646 — arXiv (en), https://arxiv.org/abs/2610.10646 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ead76be2bed0 (Metraipolis archive dc_ead76be2bed0, sha256 72ed1e93468278efb61c4b71bef2d7b4d8d1c8da7c2d30644cb7c260069b693c)

BibTeX

@misc{dcead76be2bed0,
  title = {Masked Generative Motion Planning with Geometry-Guided Token Search — arXiv:2610.10646},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.10646},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ead76be2bed0; sha256 72ed1e93468278efb61c4b71bef2d7b4d8d1c8da7c2d30644cb7c260069b693c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.10646. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Generative motion planners typically use learned trajectory priors for initial generation, while leaving test-time repair to local continuous refinement. We introduce Masked Generative Motion Planning (MGMP), which extends the learned prior from efficient parallel generation to structural repair. A masked generative transformer generates discrete trajectory candidates in parallel, and Geometry-Guided Token Search (GGTS) uses scene geometry to target where to edit and which prior-supported alternatives to evaluate. This turns refinement into an efficient search over discrete motion alternatives, enabling route-level restructuring beyond local trajectory deformation. MGMP achieves 96% success on Ring Maze and 82% repair success on Controlled Route Invalidation on Kuka, exceeding the strongest external baselines by 23 and 25 percentage points, respectively. It further generalizes to unseen layouts, additional obstacles, unseen geometries, single- and dual-arm planning, and real-world Baxter tasks.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.10646 — 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 2026-10-09T05:47:01.298Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).