Agile-VLA: Few-Shot Industrial Pose Rectification via Implicit Affordance Anchoring
This work addresses the problem of dynamic manipulation on resource-constrained edge platforms for industrial robotics, representing an incremental improvement by decoupling perception and control frequencies.
The paper tackled the conflict between high-latency semantic inference and high-frequency control in deploying Vision-Language-Action models on edge devices by introducing Agile-VLA, a hierarchical framework that uses Implicit Affordance Anchoring to map geometric visual cues into action primitives, achieving robust pose rectification of irregular workpieces with only 5-shot demonstrations on a 6-DoF manipulator.
Deploying Vision-Language-Action (VLA) models on resource-constrained edge platforms encounters a fundamental conflict between high-latency semantic inference and the high-frequency control required for dynamic manipulation. To address the challenge, this paper presents Agile-VLA, a hierarchical framework designed for industrial pose reorientation tasks on edge devices such as the NVIDIA Jetson Orin Nano. The core innovation is an Implicit Affordance Anchoring mechanism that directly maps geometric visual cues, specifically centroid and rim keypoint anchors, into structured parametric action primitives, thereby substantially reducing reliance on high-latency semantic inference during closed-loop control. By decoupling perception (10 Hz) from control (50 Hz) via an asynchronous dual-stream architecture, the system effectively mitigates the frequency mismatch inherent in edge-based robot learning. Experimental results on a standard 6-DoF manipulator demonstrate that Agile-VLA achieves robust rectification of complex, irregular workpieces using only 5-shot demonstrations through extrinsic dexterity.