arXiv Artificial Intelligence

Masked Generative Motion Planning with Geometry-Guided Token Search

1 hour ago 09.10.2026 07:00 👁 1 views
Masked Generative Motion Planning with Geometry-Guided Token Search

Quick summary

arXiv:2610.10646v1 Announce Type: cross Abstract: 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

Key takeaways

  • arXiv:2610.10646v1 Announce Type: cross Abstract: 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.

Why it matters

The importance of “Masked Generative Motion Planning with Geometry-Guided Token Search” will be measured by what changes in practice. User behavior, access conditions, verifiable performance and responsible-use outcomes are the signals worth following.

Kaynak sitede devamını oku: arXiv Artificial Intelligence ↗