探究视觉-语言-动作模型中的符号状态及其与认知架构的集成
Probing a Vision-Language-Action Model for Symbolic States and Integration into a Cognitive Architecture
AI总结：
本研究通过探测 OpenVLA 隐藏层中的符号状态表征，并将其与 DIARC 认知架构集成，在 LIBERO-spatial 任务上验证了高精度状态监控，从而提升机器人操作的可解释性与可靠性。
摘要：
视觉-语言-动作（VLA）模型通过将视觉和语言输入转化为机器人动作，有望成为通用机器人解决方案，但由于其黑箱特性以及对环境变化的敏感性，它们缺乏可靠性。相比之下，认知架构（CA）在符号推理和状态监控方面表现出色，但受限于僵化的预定义执行方式。本研究通过探测 OpenVLA 的隐藏层来揭示物体属性、关系和动作状态的符号表征，从而弥合这两种方法之间的差距，使其能够与认知架构集成，以提升可解释性和鲁棒性。通过在 LIBERO-spatial 抓取-放置任务上的实验，我们分析了符号状态在 OpenVLA 的 Llama 骨干网络不同层中的编码情况。我们的探测结果显示，在大多数层中，物体状态和动作状态的准确率始终较高（> 0.90），但与我们的假设相反，我们并未观察到物体状态比动作状态更早被编码的预期模式。我们展示了一个集成的 DIARC-OpenVLA 系统，该系统利用这些符号表征进行实时状态监控，为更具可解释性和可靠性的机器人操作奠定了基础。
英文摘要：
Vision-language-action (VLA) models hold promise as generalist robotics solutions by translating visual and linguistic inputs into robot actions, yet they lack reliability due to their black-box nature and sensitivity to environmental changes. In contrast, cognitive architectures (CA) excel in symbolic reasoning and state monitoring but are constrained by rigid predefined execution. This work bridges these approaches by probing OpenVLA's hidden layers to uncover symbolic representations of object properties, relations, and action states, enabling integration with a CA for enhanced interpretability and robustness. Through experiments on LIBERO-spatial pick-and-place tasks, we analyze the encoding of symbolic states across different layers of OpenVLA's Llama backbone. Our probing results show consistently high accuracies (> 0.90) for both object and action states across most layers, though contrary to our hypotheses, we did not observe the expected pattern of object states being encoded earlier than action states. We demonstrate an integrated DIARC-OpenVLA system that leverages these symbolic representations for real-time state monitoring, laying the foundation for more interpretable and reliable robotic manipulation.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
