CPS: Small: Neuro-Symbolic Learning and Control with High-Level Knowledge Inference

CPS：小型：具有高级知识推理的神经符号学习和控制

• 批准号: 2304863
• 负责人: Zhe Xu
• 金额: $ 50万
• 依托单位: Arizona State University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-07-01 至 2026-06-30
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2304863&HistoricalAwards=false
• 关键词: CPS; Small; Neuro; Symbolic; Learning

The use of artificial intelligence in cyber-physical systems is limited by challenges such as data availability, task environment complexity, and the need for expressive and interpretable high-level knowledge representations. To address these challenges, this project aims to develop a set of neuro-symbolic learning and control tools by integrating machine learning, control theory, and formal methods. The results are expected to find application across cyber-physical systems such as robotic systems, autonomous systems, and networked cyber-physical systems. Validation in a testbed environments should facilitate safe deployments in real-world physical environments with provable guarantees and robustness against potential adversaries.The research tasks mainly focus on improving the data efficiency, interpretability, scalability, and resiliency of the neuro-symbolic approaches in cyber-physical systems, with special focus on cyber-physical systems where extensive online interactions may not be safe or feasible, but high-level knowledge can be useful in completing tasks in complex and adversarial environments with provable correctness guarantees. Specifically, the neuro-symbolic learning and control algorithms offer the following three key features. Firstly, they incorporate template-free inference of high-level knowledge (e.g., temporal logic formulas) from uncertain data into neuro-symbolic learning to enable data-efficient reinforcement learning with both offline training and online fine-tuning. Secondly, the approaches are capable of achieving scalable and resilient reinforcement learning in multi-agent adversarial environments where high-level knowledge can be inferred for expediting the agents' learning processes. Lastly, the algorithms provide provable guarantees on complex task specifications using neuro-symbolic learning-based adaptive control with unknown dynamics. The results of this research will be shared through a range of educational activities, including undergraduate and graduate courses, as well as research workshops. Additionally, outreach programs will be implemented to engage K-12 students and diverse groups in the scientific and engineering communities and broaden their participation.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

人工智能在网络物理系统中的使用受到数据可用性、任务环境复杂性以及对表达性和可解释性高级知识表示的需求等挑战的限制。为了应对这些挑战，本项目旨在通过整合机器学习、控制理论和形式化方法，开发一套神经符号学习和控制工具。这些结果有望在网络物理系统中得到应用，如机器人系统、自主系统和网络物理系统。测试平台环境中的验证应有助于在真实物理环境中的安全部署，并具有可证明的保证和对潜在对手的鲁棒性。研究任务主要集中在提高网络物理系统中神经符号方法的数据效率，可解释性，可扩展性和弹性，特别关注广泛的在线交互可能不安全或不可行的网络物理系统，但是高级知识在复杂和对抗性环境中完成具有可证明的正确性保证的任务时是有用的。具体来说，神经符号学习和控制算法提供了以下三个关键特征。首先，它们结合了高级知识的无模板推理（例如，时间逻辑公式）从不确定数据到神经符号学习，以实现具有离线训练和在线微调的数据高效强化学习。其次，该方法能够在多智能体对抗环境中实现可扩展和弹性的强化学习，其中可以推断高级知识以加快智能体的学习过程。最后，该算法提供了可证明的保证复杂的任务规范，使用神经符号学习为基础的自适应控制与未知的动态。这项研究的结果将通过一系列教育活动，包括本科生和研究生课程，以及研究讲习班共享。此外，还将实施外展计划，以吸引K-12学生和科学和工程界的各种团体，并扩大他们的参与。该奖项反映了NSF的法定使命，并被认为值得通过使用基金会的智力价值和更广泛的影响审查标准进行评估来支持。

项目成果

Decentralized Graph-Based Multi-Agent Reinforcement Learning Using Reward Machines

• DOI: 10.1016/j.neucom.2023.126974
• 发表时间: 2021-09
• 期刊: ArXiv
• 作者: Jueming Hu;Zhe Xu;Weichang Wang;Guannan Qu;Yutian Pang;Yongming Liu

Reinforcement Learning with Temporal-Logic-Based Causal Diagrams

• DOI: 10.48550/arxiv.2306.13732
• 发表时间: 2023-06
• 期刊: ArXiv
• 作者: Yashi Paliwal;Rajarshi Roy;Jean-Raphael Gaglione;Nasim Baharisangari;D. Neider;Xiaoming Duan;U. Topcu;Zhe Xu