Safety verification of Neural-Network-based controllers: a set invariance approach
This paper presents a novel approach to ensure the safety of continuous-time linear dynamical systems controlled by a neural network (NN) based state-feedback. Our method capitalizes on the use of continuous piece-wise affine (PWA) activation functions (e.g. ReLU) which render the NN a PWA continuous function. By computing the affine regions of the latter and applying Nagumo's theorem, a subset of boundary points can effectively verify the invariance of a potentially non-convex set. Consequently, an algorithm that partitions the state space in affine regions is proposed. The scalability of our approach is thoroughly analyzed, and extensive tests are conducted to validate its effectiveness.
Code (1)
Similar Papers 제목 키워드 기반
Neural Network-assisted Interval Reachability for Systems with Control Barrier Function-Based Safe Controllers
Control Barrier Functions (CBFs) have been widely utilized in the design of optimization-based controllers and filters for dynamical systems to ensure forward invariance of a given set of safe states. While CBF-based con…
Safety Verification of Model Based Reinforcement Learning Controllers
Model-based reinforcement learning (RL) has emerged as a promising tool for developing controllers for real world systems (e.g., robotics, autonomous driving, etc.). However, real systems often have constraints imposed o…
Autonomous DrivingmodelModel-based Reinforcement Learningreinforcement-learning+2Scalable Synthesis of Verified Controllers in Deep Reinforcement Learning
There has been significant recent interest in devising verification techniques for learning-enabled controllers (LECs) that manage safety-critical systems. Given the opacity and lack of interpretability of the neural pol…
Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)End-to-End Imitation Learning with Safety Guarantees using Control Barrier Functions
Imitation learning (IL) is a learning paradigm which can be used to synthesize controllers for complex systems that mimic behavior demonstrated by an expert (user or control algorithm). Despite their popularity, IL metho…
Imitation LearningMyopically Verifiable Probabilistic Certificates for Safe Control and Learning
This paper addresses the design of safety certificates for stochastic systems, with a focus on ensuring long-term safety through fast real-time control. In stochastic environments, set invariance-based methods that restr…
Decision Making