安全クリティカル自律システムのための制御器の形式合成:発展と課題
Formal Synthesis of Controllers for Safety-Critical Autonomous Systems: Developments and Challenges
安全クリティカルな自律システムのための形式制御合成技術を、システムモデルや仕様の種類、抽象化ベース/非ベース手法、データ駆動型合成、マルチエージェントシステムのスケーラビリティまで網羅的にレビューした論文。
著者: Xiang Yin, Bingzhao Gao, Xiao Yu
分類: eess.SY, cs.RO, cs.SY
原文アブストラクト
In recent years, formal methods have been extensively used in the design of autonomous systems. By employing mathematically rigorous techniques, formal methods can provide fully automated reasoning processes with provable safety guarantees for complex dynamic systems with intricate interactions between continuous dynamics and discrete logics. This paper provides a comprehensive review of formal controller synthesis techniques for safety-critical autonomous systems. Specifically, we categorize the formal control synthesis problem based on diverse system models, encompassing deterministic, non-deterministic, and stochastic, and various formal safety-critical specifications involving logic, real-time, and real-valued domains. The review covers fundamental formal control synthesis techniques, including abstraction-based approaches and abstraction-free methods. We explore the integration of data-driven synthesis approaches in formal control synthesis. Furthermore, we review formal techniques tailored for multi-agent systems (MAS), with a specific focus on various approaches to address the scalability challenges in large-scale systems. Finally, we discuss some recent trends and highlight research challenges in this area.
