神经符号谓词学习用于语义安全机器人控制

中文摘要 AI 辅助

随着机器人在日常环境中的部署日益增多，确保其安全性已成为一个核心挑战。现有方法通常将安全要求编码为不透明的数学/逻辑公式或稠密的成本函数。虽然这些方法在特定任务中有效，但它们难以解释、与单个任务紧密耦合，并且对于为何机器人动作被视为安全或不安全提供的洞察有限。为解决这一局限性，我们提出了“神经符号谓词学习用于语义安全机器人控制”（NEUPRO），该方法利用一个可微推理器，能够从人类指定的安全知识中学习可重用的安全表示。NEUPRO允许实践者将任务相关的安全要求表达为透明的符号规则，同时使梯度能够通过这些规则传播到将原始观测映射到安全相关概念的特征提取器。因此，学习到的特征提取器（软性地）基于人类可理解的语义，支持透明的约束评估，并且可跨任务迁移。通过将可解释性与可微性相结合，NEUPRO超越了不透明的成本设计，迈向可重用的安全推理。为评估NEUPRO的能力，我们收集并发布了REASON，这是首个用于可解释机器人安全规范的真实机器人基准数据集。在REASON上的实验表明，NEUPRO学习到的安全关键特征能够跨任务泛化，缓解了传统黑盒成本公式的可解释性局限，并提供了安全违规的明确解释。

英文摘要

As robots are increasingly deployed in everyday environments, ensuring their safety has become a central challenge. Existing methods often encode safety requirements as opaque mathematical/logical formulations or dense cost functions. While effective in specific tasks, they remain difficult to interpret, tightly coupled to individual tasks, and offer limited insight into why a robot action is considered safe or unsafe. To address this limitation, we propose ``Neuro-Symbolic Predicate Learning for Semantic Safe Robot Control'' (NEUPRO), which leverages a differentiable reasoner that can learn reusable safety representations from human-specified safety knowledge. NEUPRO allows practitioners to express task-related safety requirements as transparent symbolic rules, while enabling gradients to propagate through these rules to a feature extractor that maps raw observations to safety-relevant concepts. As a result, the learned feature extractor is (softly) grounded in human-understandable semantics, supports transparent constraint evaluation, and is transferable across tasks. By coupling interpretability with differentiability, NEUPRO moves beyond opaque cost design toward reusable safety reasoning. To evaluate NEUPRO's capability, we collect and release REASON, the first real robot benchmark dataset for interpretable robot safety specification. Experiments on REASON show that NEUPRO learns safety-critical features that generalize across tasks, mitigate the interpretability limitations of conventional black-box cost formulations, and provide explicit explanations of safety violation.

发表机构

• TU Darmstadt（达姆施塔特工业大学）
• AIML group（AIML 研究组）
• IAS group（IAS 研究组）
• PEARL group（PEARL 研究组）
• Hessian AI（黑森人工智能中心）
• DFKI（德国人工智能研究中心）
• Tongji University（同济大学）
• Robotics Institute Germany（德国机器人研究所）

机构由 AI 辅助整理，请以论文原文为准。