发表机构
School of Advanced Manufacturing and Robotics, Peking University; School of Integrated Circuits, Peking University（北京大学先进制造与机器人学院; 北京大学集成电路学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出自约束推理（SCR）框架，将结构知识内化到模型决策中，以在不破坏推理的前提下，提升将人类指令翻译为线性时态逻辑（LTL）时的领域约束满足度与泛化能力。
AI 中文摘要
许多机器人任务具有时间扩展性，需要对子目标、约束及其时间顺序进行精确规范。然而人类操作员通常用自然语言传达这类任务，而自然语言本身具有模糊性、规范不足和语境依赖的特点。因此将人类指令翻译为形式化任务规范（如线性时态逻辑（Linear Temporal Logic, LTL））对实现机器人可验证、安全的执行至关重要。现有的基于大语言模型（LLM）的翻译器试图通过开放式推理或事后约束执行来弥合这一差距，但前者可能违反领域约束，后者则会破坏处理新指令所需的推理过程。本文提出自约束推理（Self-Constrained Reasoning, SCR）框架，该框架通过将结构知识内化到模型的决策过程中，而非将其作为外部过滤器施加，来缓解上述权衡问题。通过结合结构约束表示与分层决策制定公式，SCR在形式化基础的空间内引导推理，同时保持对未见指令的适应性。实验表明，SCR在领域约束满足和泛化能力两方面均有提升，为将人类意图翻译为机器人执行所需的可验证规范提供了一种有效且可解释的方法。
英文摘要
Many robotic tasks are temporally extended and demand precise specifications of subgoals, constraints, and their temporal ordering. Yet human operators typically communicate such tasks in natural language, which is inherently ambiguous, underspecified, and context dependent. Translating human instructions into formal task specifications, such as Linear Temporal Logic (LTL), is therefore essential for verifiable and safe robotic execution. Existing LLM-based translators attempt to bridge this gap through open-ended reasoning or post-hoc constraint enforcement, but the former may violate domain constraints, whereas the latter can disrupt the reasoning needed for novel instructions. This paper proposes Self-Constrained Reasoning (SCR), a framework that mitigates this trade-off by internalizing structural knowledge into the model's decision-making process rather than imposing it as an external filter. By combining a structural constraint representation with a hierarchical decision-making formulation, SCR guides reasoning within a formally grounded space while preserving adaptability to unseen instructions. Experiments show that SCR improves both domain-constraint satisfaction and generalization, providing an effective and interpretable approach for translating human intent into verifiable specifications for robotic execution.
