自然状态预测精度可能掩盖VLA读出中较弱的受控响应性

中文摘要 AI 辅助

从视觉-语言-动作（VLA）模型的内部表示中准确解码对象状态，并不能保证预测能忠实响应目标物理状态的变化。在自然观测中，对象状态、机器人配置、遮挡和任务进度会同时变化，使得上下文线索能够对预测有所贡献。在本文中，我们引入了一个评估框架，该框架通过将目标坐标与机器人上下文交叉的物理验证观测，将预测精度、目标状态响应性和上下文稳定性分离开来。我们证明，在固定的表示-读出对中，高自然轨迹精度可能与较弱的目标状态受控响应性共存。涉及表示、读出和训练数据的比较和干预表明，这三个属性提供了不同的诊断信息。此外，在基于初始状态误差和物理变量的故障预测器中加入响应性和上下文敏感性，相对于指定基线，减少了新初始化上的策略故障预测误差，而相同观测的受控平均绝对误差（MAE）也具有信息量。这些发现促使在自然预测精度之外，评估目标状态响应性和上下文稳定性，并考察它们与实际策略行为和任务结果的关系。

英文摘要

Accurately decoding object states from the internal representations of vision-language-action (VLA) models does not establish that the predictions respond faithfully to changes in the target physical state. In natural observations, object state, robot configuration, occlusion, and task progress vary together, allowing contextual cues to contribute to prediction. In this paper, we introduce an evaluation framework that separates prediction accuracy, target-state responsiveness, and context stability using physically validated observations that cross target coordinates with robot contexts. We demonstrate that high natural-trajectory accuracy can coexist with weak controlled target-state responsiveness in fixed representation-readout pairs. Comparisons and interventions involving representations, readouts, and training data show that the three properties provide distinct diagnostic information. Furthermore, adding responsiveness and context sensitivity to a failure predictor based on initial state error and physical variables reduces policy-failure prediction error on new initializations relative to the specified baseline while same-observation controlled MAE is also informative. These findings motivate evaluating target-state responsiveness and context stability alongside natural prediction accuracy, and examining their relationship to actual policy behavior and task outcomes.

发表机构

• Changwon National University（昌原国立大学）
• Chung-Ang University（中央大学）

机构由 AI 辅助整理，请以论文原文为准。