生成视觉-语言-动作模型中的动作幻觉
Action Hallucination in Generative Vision-Language-Action Models
AI总结：
研究分析生成视觉-语言-动作模型中动作幻觉的根源，揭示拓扑、精度和地平线三类障碍对动作生成的影响，提出改进模型可靠性和可信度的方法。
摘要：
机器人基础模型，如VLAs，承诺端到端生成机器人策略的广泛泛化能力。然而，其是否根本解决具身环境中的动作生成核心问题仍不清楚。本文通过分析违反物理约束的动作幻觉及其计划层面失败，揭示潜在变量生成策略中可行机器人行为与常见模型架构之间的结构不匹配。研究三种障碍——拓扑、精度和地平线，并展示它们如何引入不可避免的权衡。分析为生成机器人策略的实证失败提供了机制解释，并建议改进可靠性和可信度的原则方向，而无需放弃其表达能力。
英文摘要：
Robot Foundation Models, such as VLAs, promise end-to-end generative robot policies with broad generalization. Yet it remains unclear whether they fundamentally resolve the core problem of action generation in embodied settings, or overcome the long-standing challenges of robotics. We address this question by analyzing action hallucinations that violate physical constraints and their extension to plan-level failures. Focusing on latent-variable generative policies, we show that hallucinations can arise from structural mismatches between feasible robot behavior and common model architectures. We study three such barriers -- topological, precision, and horizon -- and show how they impose unavoidable tradeoffs. Our analysis provides mechanistic explanations for reported empirical failures of generative robot policies and suggests principled directions for improving reliability and trustworthiness, without abandoning their expressive power.
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。
