適応的ストレステストによる画像ベースNN制御器の検証
Validation of Image-Based Neural Network Controllers through Adaptive Stress Testing
画像入力のニューラルネット制御システムに対し、適応的ストレステストとNN検証を組み合わせ、故障を引き起こす最も起こりやすい画像外乱系列を探索する手法を提案し、航空機の自動走行タスクで有効性を示した。
著者: Kyle D. Julian, Ritchie Lee, Mykel J. Kochenderfer
分類: cs.RO, cs.SY, eess.SY
原文アブストラクト
Neural networks have become state-of-the-art for computer vision problems because of their ability to efficiently model complex functions from large amounts of data. While neural networks can be shown to perform well empirically for a variety of tasks, their performance is difficult to guarantee. Neural network verification tools have been developed that can certify robustness with respect to a given input image; however, for neural network systems used in closed-loop controllers, robustness with respect to individual images does not address multi-step properties of the neural network controller and its environment. Furthermore, neural network systems interacting in the physical world and using natural images are operating in a black-box environment, making formal verification intractable. This work combines the adaptive stress testing (AST) framework with neural network verification tools to search for the most likely sequence of image disturbances that cause the neural network controlled system to reach a failure. An autonomous aircraft taxi application is presented, and results show that the AST method finds failures with more likely image disturbances than baseline methods. Further analysis of AST results revealed an explainable cause of the failure, giving insight into the problematic scenarios that should be addressed.
