用加权时序逻辑生成机器人策略的简洁可解释说明。
Neuro-Symbolic Generation of Explanations for Robot Policies with Weighted Signal Temporal Logic
- 结合神经网络与符号逻辑，生成可读的策略描述。
- 在三个仿真环境中优于基线，保持准确率同时提升解释质量。
- 提出新评估指标，适合关注安全透明决策的研究者。
基于神经网络的机器人策略在诸多应用中表现优异，但缺乏人类可理解性，限制了其在高安全性场景中的部署。为此，我们提出一种神经符号解释框架，通过生成加权信号时序逻辑（wSTL）规范，以可解释形式描述机器人策略。现有方法常产生冗长、不一致且松散的解释，难以提供有效洞察。我们通过谓词过滤、正则化与迭代剪枝构建简化流程，解决上述问题。同时引入三项新解释性评估指标——简洁性、一致性与严格性，超越传统分类性能评价。在三个仿真机器人环境中的实验表明，该方法在保持分类准确率的前提下，显著提升了wSTL解释的简洁性、一致性和严格性。本工作连接策略学习与形式化方法，推动机器人决策更安全、更透明。
原文摘要 · Abstract (English)
Neural network-based policies have demonstrated success in many robotic applications, but often lack human-explanability, which poses challenges in safety-critical deployments. To address this, we propose a neuro-symbolic explanation framework that generates a weighted signal temporal logic (wSTL) specification to describe a robot policy in a interpretable form. Existing methods typically produce explanations that are verbose and inconsistent, which hinders explainability, and loose, which do not give meaningful insights into the underlying policy. We address these issues by introducing a simplification process consisting of predicate filtering, regularization, and iterative pruning. We also introduce three novel explainability evaluation metrics -- conciseness, consistency, and strictness -- to assess explanation quality beyond conventional classification metrics. Our method is validated in three simulated robotic environments, where it outperforms baselines in generating concise, consistent, and strict wSTL explanations without sacrificing classification accuracy. This work bridges policy learning with formal methods, contributing to safer and more transparent decision-making in robotics.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。