敵対的画像を用いた学習ベース自律ステアリングのロバスト性向上
Improving Robustness of Learning-based Autonomous Steering Using Adversarial Images
画像品質の変動に対する学習アルゴリズムのロバスト性を分析し、感度分析に基づいて「学習によるステアリング」の性能を最大48%改善する手法を提案した論文。
著者: Yu Shen, Laura Zheng, Manli Shu, Weizi Li, Tom Goldstein, Ming C. Lin
分類: cs.CV, cs.LG, cs.RO
原文アブストラクト
For safety of autonomous driving, vehicles need to be able to drive under various lighting, weather, and visibility conditions in different environments. These external and environmental factors, along with internal factors associated with sensors, can pose significant challenges to perceptual data processing, hence affecting the decision-making and control of the vehicle. In this work, we address this critical issue by introducing a framework for analyzing robustness of the learning algorithm w.r.t varying quality in the image input for autonomous driving. Using the results of sensitivity analysis, we further propose an algorithm to improve the overall performance of the task of "learning to steer". The results show that our approach is able to enhance the learning outcomes up to 48%. A comparative study drawn between our approach and other related techniques, such as data augmentation and adversarial training, confirms the effectiveness of our algorithm as a way to improve the robustness and generalization of neural network training for autonomous driving.
