4 papers
Recoverability Is a Subspace Property: A Benchmark for Certified State Estimation from Partial PDE Observations
Qingwei Dong, Peng Zeng, Guangxi Wan +3
When reconstructing the hidden state of a partial differential equation (PDE) system from partial observations, aggregate prediction error measures performance on a given data dist…
Generator-Independent Runtime Assurance under Partial Observation
Guangxi Wan, Yongbo Xie, Yuqi Liu +4
Proposal-based controllers---learned policies, language-model planners, and other black-box \emph{generators}---are increasingly deployed behind runtime verification gates. We ask…
Observation Design for Certified Control Authority: Projection--Estimability Separation and Active-Face Equivalence
Guangxi Wan, Hualong Du, Yuqi Liu +4
A sound runtime admission gate executes only actions it can certify, and certifies only what its observations support. This paper asks how observations should be designed to maximi…
Logic-informed reinforcement learning for cross-domain optimization of large-scale cyber-physical systems
Guangxi Wan, Peng Zeng, Xiaoting Dong +6
Cyber-physical systems (CPS) require the joint optimization of discrete cyber actions and continuous physical parameters under stringent safety logic constraints. However, existing…