paper-with-me

홈 › Papers

Convex Computations for Controlled Safety Invariant Sets of Black-box Discrete-time Dynamical Systems

2025-04-02 · Taoran Wu, Yiling Xue, Jingduo Pan, Dejin Ren, Arvind Easwaran, Bai Xue

Identifying controlled safety invariant sets (CSISs) is essential in safety-critical applications. This paper tackles the problem of identifying CSISs for black-box discrete-time systems, where the model is unknown and only limited simulation data is accessible. Traditionally, a CSIS is defined as a subset of a safe set, encompassing initial states for which a control input exists that keeps the system within the set at the next time step-this is referred to as the one-step invariance property. However, the requirement for one-step invariance can be equivalently translated into a stricter condition of `always-invariance'', meaning that there exist control inputs capable of keeping the system within this set indefinitely. Such a condition may prove overly stringent or impractical for black-box systems, where predictions can become unreliable beyond a single time step or a limited number of finite time steps. To overcome the challenges posed by black-box systems, we reformulate the one-step invariance property in a `Probably Approximately Correct'' (PAC) sense. This approach allows us to assess the probability that a control input exists to keep the system within the CSIS at the next time step, with a predefined level of confidence. If the system successfully remains within the set at the next time step, we can then reapply the invariance evaluation to the new state, thereby facilitating a recursive assurance of invariance. Our method employs barrier functions and scenario optimization, resulting in a linear programming method to estimate PAC CSISs. Finally, the effectiveness of our approach is demonstrated on several examples.

📄 PDF Abstract BibTeX arXiv:2504.01638

Code (1)

pcsis/pcsis 공식 구현

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

An Invariant Set Construction Method, Applied to Safe Coordination of Thermostatic Loads

2022-02-11 · Sunho Jang, Necmiye Ozay, Johanna L. Mathieu

We consider the problem of coordinating a collection of switched subsystems under both local and global constraints for safe operation of the system. Although an invariant set can be leveraged to construct a safety-guara…

Minimal Intervention Shared Control with Guaranteed Safety under Non-Convex Constraints

2025-07-03 · Shivam Chaubey, Francesco Verdoja, Shankar Deka, Ville Kyrki arxiv

Shared control combines human intention with autonomous decision-making. At the low level, the primary goal is to maintain safety regardless of the user's input to the system. However, existing shared control methods-bas…

Plug-and-Play Secondary Control for Safety of LTI Systems under Attacks

2022-12-01 · Yankai Lin, Michelle S. Chong, Carlos Murguia

We consider the problem of controller design for linear time-invariant cyber-physical systems (CPSs) controlled via networks. Specifically, we adopt the set-up that a controller has already been designed to stabilize the…

Compositional Inductive Invariant Based Verification of Neural Network Controlled Systems

2023-12-17 · Yuhao Zhou, Stavros Tripakis

The integration of neural networks into safety-critical systems has shown great potential in recent years. However, the challenge of effectively verifying the safety of Neural Network Controlled Systems (NNCS) persists. …

ShardNet: Training Neural Controllers with Hard, Non-Convex Constraints

2026-06-29 · Long Kiu Chung, Shreyas Kousik arxiv

While neural network control policies are powerful, their deployment on safety critical systems depends on ensuring that they obey strict constraints. Existing work often treats safety as a metric to optimize for, which …