基于法律推理的立法世界模型规划
Legislating World-Model-Based Planning with Legal Reasoning
- Cognizant Responsible AI Lab, Cognizant（Cognizant负责任AI实验室，Cognizant）
- Cognizant AI Lab, Cognizant（Cognizant AI实验室，Cognizant）
- Washington University（华盛顿大学）
- Central Queensland University（中央昆士兰大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出基于可废止道义逻辑的法律规划栈，利用学习的世界模型实现事前立法治理，在模拟机器人任务中显著提升法律遵守率，并量化了接地与本体同构差距。
AI中文摘要：
随着机器人系统日益通用化，需要法律规范将其融入社会。本文扩展了将法律源文本与其编码对齐的同构问题，并衡量了机器人规范控制的两个关键挑战：（1）\textit{接地同构差距}，即感知误差为法律推理接地了错误的原子事实；（2）\textit{本体同构差距}，即一个法律结论可被忠实翻译成多种规划约束。本文引入了一个法律规划栈，采用可废止道义逻辑（DDL）来约束运动规划器。该栈利用学习到的世界模型进行规划并提供法律背景，实现\textit{事前}治理，在非法动作执行前进行干预。该系统部署在一个模拟机器人手臂上，该手臂在$3\ imes3$网格上推动一个立方体。研究发现：（1）立法智能体比非立法智能体更频繁地遵守法律，且对感知不确定性建模进一步提高了遵守率；（2）法律推理在运行时高效执行，其裁决可审计；（3）该栈适应了外生信号和内生规则变化。两个差距均被测量：（4）世界模型和探针误差破坏了DDL推理器的事实输入；（5）单一法律可被解释为多种忠实的度量解释，导致遵守率截然不同。因此，\textit{事前}立法按预期发挥作用，通过标准化从法律到运行时约束的映射以及改进从感知的事实接地来缩小这些差距，将产生使机器人行为与社会规范对齐的稳健法律。
英文摘要：
As robotic systems grow more general, legal norms are needed to integrate them into society. This paper extends the isomorphism problem of aligning legal source texts with their encodings, and measures two key challenges to robot normative control: (1) the grounding isomorphism gap, where perception error grounds false atoms for legal reasoning, and (2) the ontological isomorphism gap, where one legal conclusion admits many faithful translations into planning constraints. The paper introduces a legal planning stack that employs Defeasible Deontic Logic (DDL) to constrain a motion planner. The stack leverages learned world models to plan and to provide legal context, enabling ex ante governance that intervenes before an illegal action is executed. It was deployed on a simulated robot arm pushing a cube across a 3x3 grid. The findings were (1) the legislated agent abided substantially more often than the non-legislated one, and modeling perception uncertainty lifted abidance even further, (2) the legal reasoning ran efficiently at runtime and its verdicts were auditable, and (3) the stack adapted to exogenous signals and endogenous rule changes. Both gaps were measured: (4) world model and probe error corrupted the factual input for the DDL reasoner, and (5) a single law admitted several faithful metric interpretations yielding drastically different abidance. Thus, ex ante legislation functions as intended, and closing these gaps with a standardized mapping from the law to runtime constraints and improved fact grounding from perception will yield robust laws that align robot behavior with society's norms. Project page: https://dylanwaldner-cail.github.io/Legislated-Planner/.
