Safety Filter Design for Neural Network Systems via Convex Optimization
With the increase in data availability, it has been widely demonstrated that neural networks (NN) can capture complex system dynamics precisely in a data-driven manner. However, the architectural complexity and nonlinearity of the NNs make it challenging to synthesize a provably safe controller. In this work, we propose a novel safety filter that relies on convex optimization to ensure safety for a NN system, subject to additive disturbances that are capable of capturing modeling errors. Our approach leverages tools from NN verification to over-approximate NN dynamics with a set of linear bounds, followed by an application of robust linear MPC to search for controllers that can guarantee robust constraint satisfaction. We demonstrate the efficacy of the proposed framework numerically on a nonlinear pendulum system.
Code (1)
Similar Papers 제목 키워드 기반
Safety Filter for Robust Disturbance Rejection via Online Optimization
Disturbance rejection in high-precision control applications can be significantly improved upon via online convex optimization (OCO). This includes classical techniques such as recursive least squares (RLS) and more rece…
FBMC Prototype Filter Design via Convex Optimization
In this work, we propose a prototype filter design for Filter Bank MultiCarrier (FBMC) systems based on convex optimization, aiming superior spectrum features while maintaining a high symbol reconstruction quality. Initi…
Vocal Bursts Type PredictionLearning Predictive Safety Filter via Decomposition of Robust Invariant Set
Ensuring safety of nonlinear systems under model uncertainty and external disturbances is crucial, especially for real-world control tasks. Predictive methods such as robust model predictive control (RMPC) require solvin…
Model Predictive ControlReinforcement Learning (RL)Beampattern and Robust Doppler Filter Design for Spatial Modulation Based Joint RadCom Systems
Joint radar and communication (RadCom) systems have been proposed to achieve the spectrum sharing between radar and communication in recent years. However, the joint RadCom systems cause the clutter modulation and the pe…
Differentially Flat Learning-based Model Predictive Control Using a Stability, State, and Input Constraining Safety Filter
Learning-based optimal control algorithms control unknown systems using past trajectory data and a learned model of the system dynamics. These controllers use either a linear approximation of the learned dynamics, tradin…
Computational EfficiencyModel Predictive Control