Reliability-aware Execution Gating for Near-field and Off-axis Vision-guided Robotic Alignment

TL;DR

This paper introduces a reliability-aware execution gating mechanism that enhances the robustness of vision-guided robotic alignment by evaluating geometric consistency and configuration risk before execution, thereby reducing failures without altering pose estimation accuracy.

Contribution

The paper presents a novel execution-level gating approach that improves reliability in robotic alignment tasks, independent of pose estimation methods, by assessing geometric and configuration risks prior to execution.

Findings

Significantly increased task success rates.

Reduced execution variance and tail-risk behavior.

Compatible with classical and learning-based pose estimators.

Abstract

Vision-guided robotic systems are increasingly deployed in precision alignment tasks that require reliable execution under near-field and off-axis configurations. While recent advances in pose estimation have significantly improved numerical accuracy, practical robotic systems still suffer from frequent execution failures even when pose estimates appear accurate. This gap suggests that pose accuracy alone is insufficient to guarantee execution-level reliability. In this paper, we reveal that such failures arise from a deterministic geometric error amplification mechanism, in which small pose estimation errors are magnified through system structure and motion execution, leading to unstable or failed alignment. Rather than modifying pose estimation algorithms, we propose a Reliability-aware Execution Gating mechanism that operates at the execution level. The proposed approach evaluates geometric consistency and configuration risk before execution, and selectively rejects or scales high-risk pose updates. We validate the proposed method on a real UR5 robotic platform performing single-step visual alignment tasks under varying camera-target distances and off-axis configurations. Experimental results demonstrate that the proposed execution gating significantly improves task success rates, reduces execution variance, and suppresses tail-risk behavior, while leaving average pose accuracy largely unchanged. Importantly, the proposed mechanism is estimator-agnostic and can be readily integrated with both classical geometry-based and learning-based pose estimation pipelines. These results highlight the importance of execution-level reliability modeling and provide a practical solution for improving robustness in near-field vision-guided robotic systems.