Research papers · Posted 2024.11.15 · Preprint
Observer-Based Safety Monitoring of Nonlinear Dynamical Systems with Neural Networks via Quadratic Constraint Approach
Observer-Based Safety Monitoring of Nonlinear Dynamical Systems with Neural Networks via Quadratic Constraint Approach
Overview
The authors construct interval observers for nonlinear systems with neural components using quadratic constraints and Lyapunov conditions. Optimization-based design bounds state-estimation errors, illustrated through simulated lateral vehicle control.
Version: v1