ShieldNN: A Provably Safe NN Filter for Unsafe NN Controllers

Abstract

In this paper, we develop a novel closed-form Control Barrier Function (CBF) and associated controller shield for the Kinematic Bicycle Model (KBM) with respect to obstacle avoidance. The proposed CBF and shield -- designed by an algorithm we call ShieldNN -- provide two crucial advantages over existing methodologies. First, ShieldNN considers steering and velocity constraints directly with the non-affine KBM dynamics; this is in contrast to more general methods, which typically consider only affine dynamics and do not guarantee invariance properties under control constraints. Second, ShieldNN provides a closed-form set of safe controls for each state unlike more general methods, which typically rely on optimization algorithms to generate a single instantaneous for each state. Together, these advantages make ShieldNN uniquely suited as an efficient Multi-Obstacle Safe Actions (i.e. multiple-barrier-function shielding) during training time of a Reinforcement Learning (RL) enabled Neural Network controller. We show via experiments that ShieldNN dramatically increases the completion rate of RL training episodes in the presence of multiple obstacles, thus establishing the value of ShieldNN in training RL-based controllers.

References in corpus (12)

• Neural Lander: Stable Drone Landing Control using Learned Dynamics
• CARLA: An Open Urban Driving Simulator
• Lyapunov-based Safe Policy Optimization for Continuous Control
• Training robust neural networks using Lipschitz bounds
• A Control Barrier Perspective on Episodic Learning via Projection-to-State Safety
• End-to-End Safe Reinforcement Learning through Barrier Functions for Safety-Critical Continuous Control Tasks
• Temporal Logic Guided Safe Reinforcement Learning Using Control Barrier Functions
• Decoupling feature extraction from policy learning: assessing benefits of state representation learning in goal based robotics
• Safe Multi-Agent Interaction through Robust Control Barrier Functions with Learned Uncertainties
• Learning-based Model Predictive Control for Safe Exploration
• Safe Reinforcement Learning for Autonomous Vehicles through Parallel Constrained Policy Optimization
• Robust Regression for Safe Exploration in Control

Cited by in corpus (4)

• Learning Hybrid Control Barrier Functions from Data
• BarrierNet: A Safety-Guaranteed Layer for Neural Networks
• Provably Correct Training of Neural Network Controllers Using Reachability Analysis
• Learn Zero-Constraint-Violation Policy in Model-Free Constrained Reinforcement Learning