Improving Robustness of Learning-based Autonomous Steering Using Adversarial Images
This work addresses safety-critical robustness issues in autonomous driving for vehicles operating under diverse conditions, representing an incremental improvement over existing techniques like data augmentation and adversarial training.
The paper tackled the problem of improving robustness in learning-based autonomous steering by analyzing sensitivity to varying image quality and proposing an algorithm that enhanced learning outcomes by up to 48%.
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.