用图神经网络和流匹配学习通用时序逻辑规划，速度快且泛化强。
TeLoGraF: Temporal Logic Planning via Graph-encoded Flow Matching
- 用图神经网络编码时序逻辑，结合流匹配学习策略
- 在5个环境上达成90%以上时序逻辑满足率，推理快10-100倍
- 支持任意系统动力学，适合复杂逻辑与分布外任务
学习满足信号时序逻辑（STL）规范的复杂任务对许多实际应用至关重要。然而，以往方法多局限于固定或参数化STL规范，因缺乏多样化的STL数据集及有效提取时序逻辑信息的编码器。本文提出TeLoGraF：基于图编码的时序逻辑流匹配方法，利用图神经网络（GNN）编码器与流匹配技术，学习通用STL规范的解。我们识别出4种常见STL模板，构建了包含20万条规范及其对应演示的数据集。在5个仿真环境中进行实验，涵盖二维空间中的简单动力模型至高维7自由度Franka Panda机械臂和Ant四足机器人导航。结果表明，本方法在时序逻辑满足率上优于其他基线。相比经典STL规划算法，推理速度提升10-100倍，且适用于任意系统动力学。此外，图编码方法展现出解决复杂STL的能力，并具备对分布外STL规范的鲁棒性。代码已开源：https://github.com/mengyuest/TeLoGraF
原文摘要 · Abstract (English)
Learning to solve complex tasks with signal temporal logic (STL) specifications is crucial to many real-world applications. However, most previous works only consider fixed or parametrized STL specifications due to the lack of a diverse STL dataset and encoders to effectively extract temporal logic information for downstream tasks. In this paper, we propose TeLoGraF, Temporal Logic Graph-encoded Flow, which utilizes Graph Neural Networks (GNN) encoder and flow-matching to learn solutions for general STL specifications. We identify four commonly used STL templates and collect a total of 200K specifications with paired demonstrations. We conduct extensive experiments in five simulation environments ranging from simple dynamical models in the 2D space to high-dimensional 7DoF Franka Panda robot arm and Ant quadruped navigation. Results show that our method outperforms other baselines in the STL satisfaction rate. Compared to classical STL planning algorithms, our approach is 10-100X faster in inference and can work on any system dynamics. Besides, we show our graph-encoding method's capability to solve complex STLs and robustness to out-distribution STL specifications. Code is available at https://github.com/mengyuest/TeLoGraF
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。