Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Li, Dachong, Chen, ZhuangZhuang, Zhang, Jin, Li, Jianqiang
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2604.21241
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908988108439552
author Li, Dachong
Chen, ZhuangZhuang
Zhang, Jin
Li, Jianqiang
author_facet Li, Dachong
Chen, ZhuangZhuang
Zhang, Jin
Li, Jianqiang
contents Vision--Language--Action (VLA) models often use intermediate representations to connect multimodal inputs with continuous control, yet spatial guidance is often injected implicitly through latent features. We propose $CorridorVLA$, which predicts sparse spatial anchors as incremental physical changes (e.g., $Δ$-positions) and uses them to impose an explicit tolerance region in the training objective for action generation. The anchors define a corridor that guides a flow-matching action head: trajectories whose implied spatial evolution falls outside it receive corrective gradients, while minor deviations from contacts and execution noise are permitted. On the more challenging LIBERO-Plus benchmark, CorridorVLA yields consistent gains across both SmolVLA and GR00T, improving success rate by $3.4\%$--$12.4\%$ over the corresponding baselines; notably, our GR00T-Corr variant reaches a success rate of $83.21\%$. These results indicate that action-aligned physical cues can provide direct and interpretable constraints for generative action policies, complementing spatial guidance encoded in visual or latent forms. Code is available at https://github.com/corridorVLA.
format Preprint
id arxiv_https___arxiv_org_abs_2604_21241
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle CorridorVLA: Explicit Spatial Constraints for Generative Action Heads via Sparse Anchors
Li, Dachong
Chen, ZhuangZhuang
Zhang, Jin
Li, Jianqiang
Robotics
Artificial Intelligence
Vision--Language--Action (VLA) models often use intermediate representations to connect multimodal inputs with continuous control, yet spatial guidance is often injected implicitly through latent features. We propose $CorridorVLA$, which predicts sparse spatial anchors as incremental physical changes (e.g., $Δ$-positions) and uses them to impose an explicit tolerance region in the training objective for action generation. The anchors define a corridor that guides a flow-matching action head: trajectories whose implied spatial evolution falls outside it receive corrective gradients, while minor deviations from contacts and execution noise are permitted. On the more challenging LIBERO-Plus benchmark, CorridorVLA yields consistent gains across both SmolVLA and GR00T, improving success rate by $3.4\%$--$12.4\%$ over the corresponding baselines; notably, our GR00T-Corr variant reaches a success rate of $83.21\%$. These results indicate that action-aligned physical cues can provide direct and interpretable constraints for generative action policies, complementing spatial guidance encoded in visual or latent forms. Code is available at https://github.com/corridorVLA.
title CorridorVLA: Explicit Spatial Constraints for Generative Action Heads via Sparse Anchors
topic Robotics
Artificial Intelligence
url https://arxiv.org/abs/2604.21241