Newest papers

SPAR: Search-trained Push Action Ranker for Efficient Navigation Among Movable Obstacles

Dhruv Metha Ramesh, Tri-An Nguyen, Junshan Huang, Jingjin Yu, Kostas E. Bekris, Abdeslam Boularias · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.28362 · cited by 0 works (OpenAlex) · open-access PDF

Spanish

Navegación Entre Obstáculos Movibles (NAMO) requiere que un robot reorganice objetos que bloquean el acceso a su objetivo. Para un robot empujador, el progreso puede depender de un impulso de configuración que permite una apertura posterior sin limpiar un paso por sí mismo. El número de secuencias candidatas puede crecer exponencialmente con la longitud de la secuencia, haciendo que la búsqueda basada en la física sea costosa. Introducimos el Search-trained Push Action Ranker (SPAR), que aprende a priorizar los primitivos empujados de los resultados de búsqueda simulados. Las búsquedas sobre secuencias de hasta dos empujos por objeto proporcionan supervisión que distingue las aberturas inmediatas de las secuencias de configuración. Un transformador entrenado en búsqueda basada en regresión y ranking de bús

Machine translation (Meta M2M100); the English original follows.

Abstract

Navigation Among Movable Obstacles (NAMO) requires a robot to rearrange objects that block access to its goal. For a pushing robot, progress may depend on a setup push that enables a later opening without itself clearing a passage. The number of candidate sequences can grow exponentially with sequence length, making physics-based search costly. We introduce the Search-trained Push Action Ranker (SPAR), which learns to prioritize push primitives from simulated search outcomes. Searches over sequences of up to two pushes per object provide supervision that distinguishes immediate openings from setup pushes. A transformer trained with regression and ranking losses scores primitives using contact tokens conditioned on scene geometry and reachability regions. The same model guides simulator evaluations in SPAR Search and selects actions for direct execution in SPAR Policy. Both modes solve successive keyhole problems that open access to neighboring free-space regions within a NAMO planner. Across successful runs on $300$ simulated two-push keyhole problems, SPAR Search reduces median simulator calls by $7.0\times$, leading to a $3.8\times$ reduction in planning time relative to Random Search. Without retraining, the same ranker guides search on $600$ keyhole problems which have no solution within two pushes. At a depth limit of five pushes, SPAR Search achieves $50.7\%$ success within $100$ simulator calls, compared with $20.2\%$ for Random Search. These gains carry over to NAMO planning: on hard simulated scenes, SPAR Search achieves $47\%$ success within $100$ simulator calls, compared with $21\%$ for Random Search. In real-robot experiments, SPAR Policy succeeds in $37/40$ trials without a physics-based digital twin, compared with $33/40$ for SPAR Search and $27/40$ for Random Search.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Spar, Computer science, Simulation, Random search, Artificial intelligence, Computer vision

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange