paper-with-me

Papers

Small-Gain Theorem for Safety Verification under High-Relative-Degree Constraints

2022-04-09 · Ziliang Lyu, Xiangru Xu, Yiguang Hong

This paper develops a small-gain technique for the safety analysis and verification of interconnected systems with high-relative-degree safety constraints. In this technique, input-to-state safety (ISSf) is used to characterize how the safety of a subsystem is influenced by the external input, and ISSf-barrier functions (ISSf-BFs) with high relative degree are employed to capture the safety of subsystems. With a coordination transform, the relationship between ISSf-BFs and the existing high-relative-degree (or high-order) barrier functions is established in order to simplify the ISSf analysis. With the help of high-relative-degree ISSf-BFs, a small-gain theorem is proposed for safety verification. It is shown that, under the small-gain condition, i) the interconnection of ISSf subsystems is still ISSf; and ii) the overall interconnected system is input-to-state stable (ISS) with respect to the compositional safe set. The effectiveness of the proposed small-gain theorem is illustrated on the output-constrained decentralized control of two inverted pendulums connected by a spring mounted on two carts.

📄 PDF Abstract BibTeX arXiv:2204.04376

Code (0)

등록된 구현이 없습니다.

Tasks

Vocal Bursts Intensity Prediction

Similar Papers 제목 키워드 기반

Small-Gain Theorem for Safety Verification of Interconnected Systems

2020-11-18

A small-gain theorem in the formulation of barrier function is developed in this work for safety verification of interconnected systems. This result is helpful to verify input-to-state safety (ISSf) of the overall system…

Information-Theoretic Limits of Safety Verification for Self-Improving Systems

2026-03-30 · Arsenios Scrivens arxiv

Can a safety gate permit unbounded beneficial self-modification while maintaining bounded cumulative risk? We formalize this question through dual conditions -- requiring sum delta_n < infinity (bounded risk) and sum TPR…

No Certificate for Alignment: Two Independent Impossibilities and the Pareto Frontier of Achievable Safety Guarantees

2026-03-08 · Ayushi Agarwal arxiv

We argue that formal certification of AI alignment over open-ended or unbounded input domains is impossible under standard assumptions in computational complexity and learning theory, and characterise what remains achiev…

Towards a Certified Proof Checker for Deep Neural Network Verification

2023-07-12 · Remi Desmartin, Omri Isac, Grant Passmore, Kathrin Stark 외

Recent developments in deep neural networks (DNNs) have led to their adoption in safety-critical systems, which in turn has heightened the need for guaranteeing their safety. These safety properties of DNNs can be proven…

CheckINN: Wide Range Neural Network Verification in Imandra (Extended)

2022-07-21 · Remi Desmartin, Grant Passmore, Ekaterina Komendantskaya, Matthew Daggitt

Neural networks are increasingly relied upon as components of complex safety-critical systems such as autonomous vehicles. There is high demand for tools and methods that embed neural network verification in a larger ver…

Autonomous Vehicles