Masked Generative Motion Planning with Geometry-Guided Token
Overview
A new framework, MGMP, uses masked transformers and geometry-guided token search for efficient motion planning, achieving 96% success in Ring Maze and 25% higher repair success on Kuka compared to baselines, with generalization to new environments and real-world tasks.
Generated from attributed reports · Updated 56 minutes ago
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
No current evidence-backed claims. Missing information remains not reported.
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsMasked Generative Motion Planning with Geometry-Guided Token Search
This research proposes MGMP, a generative motion planning framework that uses masked transformers and geometry-guided token search to enable efficient route-level restructuring. It achieves 96% success on Ring Maze and 25% higher repair success than baselines on Kuka, with generalization to new layouts, obstacles, and real-world tasks.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).