ニューラルネット制御の自動運転レースカーの安全性検証ケーススタディ
Case Study: Verifying the Safety of an Autonomous Racing Car with a Neural Network Controller
LiDAR生データを入力とするNN制御の自動運転レースカーで検証手法の限界を探り、実機実験でsim2realギャップと安全性の関係を調べた。
著者: Radoslav Ivanov, Taylor J. Carpenter, James Weimer, Rajeev Alur, George J. Pappas, Insup Lee
分類: eess.SY, cs.RO, cs.SY
原文アブストラクト
This paper describes a verification case study on an autonomous racing car with a neural network (NN) controller. Although several verification approaches have been proposed over the last year, they have only been evaluated on low-dimensional systems or systems with constrained environments. To explore the limits of existing approaches, we present a challenging benchmark in which the NN takes raw LiDAR measurements as input and outputs steering for the car. We train a dozen NNs using two reinforcement learning algorithms and show that the state of the art in verification can handle systems with around 40 LiDAR rays, well short of a typical LiDAR scan with 1081 rays. Furthermore, we perform real experiments to investigate the benefits and limitations of verification with respect to the sim2real gap, i.e., the difference between a system's modeled and real performance. We identify cases, similar to the modeled environment, in which verification is strongly correlated with safe behavior. Finally, we illustrate LiDAR fault patterns that can be used to develop robust and safe reinforcement learning algorithms.
