Quantifying Safety of Learning-based Self-Driving Control Using Almost-Barrier Functions

We will describe the sampling-based learning procedures Safe path-tracking control is crucial for reliable autonomous for constructing candidate neural barrier functions, and driving. Widely-adopted control methods [1], [2] have inherent certification procedures that utilize robustness analysis for difficulty with nonlinearity and uncertainty that cannot neural networks to certify regions where the barrier conditions be ignored when the vehicles are operating at relatively high are fully satisfied. Our approach is built on recent advances in speed or under adverse road conditions. Controllers obtained robustness certification of neural networks [10], [11], which from deep learning methods have shown great promise in a allows us to rigorously bound the Lie derivative values of the variety of application [3], [4]. However, neural networks are learned neural barrier function. With these methods, we are known to be highly nonlinear and complex, preventing them able to train and certify barrier functions with small region from being easily analyzed as classical controllers such as of boundary violations: 99% of the barrier region is fully Stanley [5] or Model Predictive Control (MPC) [2], [6]. In this certified for the kinematic vehicle model, 86% for the highly paper, we propose methods for the quantitative safety analysis nonlinear dynamic model with inertial effects and lateral of learning-based neural controllers by synthesizing and slip, and 91% in the TORCS environment with high-fidelity certifying neural almost-barrier functions, for path-tracking vehicle dynamics simulation (Fig.1). We visualize the certified with only black-box access to high-fidelity simulations of regions (in blue contour) and the sparse uncertified regions (in nonlinear vehicle dynamics.