AnchorRefine: Synergy-Manipulation Based on Trajectory Anchor and Residual Refinement for Vision-Language-Action Models

arXiv:2604.17787v1 Announce Type: new Abstract: Precision-critical manipulation requires both global trajectory organization and local execution correction, yet most vision-language-action (VLA) policies generate actions within a single unified space. This monolithic formulation forces macro-level transport and micro-level refinement to be optimized under the same objective, causing large motions to dominate learning while suppressing small but failure-critical corrective signals. In contrast, human manipulation is structured by global movement planning together with continuous local adjustment during execution. Motivated by this principle, we propose AnchorRefine, a hierarchical framework that factorizes VLA action modeling into trajectory anchor and residual refinement. The anchor planner predicts a coarse motion scaffold, while the refinement module corrects execution-level deviations to improve geometric and contact precision. We further introduce a decision-aware gripper refinement mechanism to better capture the discrete and boundary-sensitive nature of gripper control. Experiments on LIBERO, CALVIN, and real-robot tasks demonstrate that AnchorRefine consistently improves both regression-based and diffusion-based VLA backbones, yielding gains of up to 7.8% in simulation success rate and 18% in real-world success rate.

Related

• HiF-VLA: Hindsight, Insight and Foresight through Motion Representation for Vision-Language-Action Models
• ReconVLA: An Uncertainty-Guided and Failure-Aware Vision-Language-Action Framework for Robotic Control
• Adaptive Action Chunking at Inference-time for Vision-Language-Action Models
• HiVLA: A Visual-Grounded-Centric Hierarchical Embodied Manipulation System
• V-CAGE: Vision-Closed-Loop Agentic Generation Engine for Robotic Manipulation

Source: arXiv cs.RO | 2026-04-21