In this paper, we propose a method for addressing the issue of unnoticed catastrophic deployment and domain shift in neural networks for semantic segmentation in autonomous driving. Our approach is based on the idea that deep learning-based perception for autonomous driving is uncertain and best represented as a probability distribution. As autonomous vehicles' safety is paramount, it is crucial for perception systems to recognize when the vehicle is leaving its operational design domain, anticipate hazardous uncertainty, and reduce the performance of the perception system. To address this, we propose to encapsulate the neural network under deployment within an uncertainty estimation envelope that is based on the epistemic uncertainty estimation through the Monte Carlo Dropout approach. This approach does not require modification of the deployed neural network and guarantees expected model performance. Our defensive perception envelope has the capability to estimate a neural network's performance, enabling monitoring and notification of entering domains of reduced neural network performance under deployment. Furthermore, our envelope is extended by novel methods to improve the application in deployment settings, including reducing compute expenses and confining estimation noise. Finally, we demonstrate the applicability of our method for multiple different potential deployment shifts relevant to autonomous driving, such as transitions into the night, rainy, or snowy domain. Overall, our approach shows great potential for application in deployment settings and enables operational design domain recognition via uncertainty, which allows for defensive perception, safe state triggers, warning notifications, and feedback for testing or development and adaptation of the perception stack.

翻译：本文提出了一种方法，用于解决自动驾驶中语义分割神经网络在部署时因未被察觉的灾难性迁移和领域偏移问题。我们的方法基于以下观点：基于深度学习的自动驾驶感知具有不确定性，最好以概率分布形式表示。由于自动驾驶车辆的安全性至关重要，感知系统必须能够识别车辆何时偏离其运行设计域、预判危险不确定性并降低感知系统性能。为此，我们建议将部署中的神经网络封装在一个基于蒙特卡洛丢弃法认知不确定性估计的不确定性估计包络中。该方法无需修改已部署的神经网络，且能保证预期的模型性能。我们的防御性感知包络能够评估神经网络性能，从而实现在部署过程中对神经网络性能下降区域的监控与预警。此外，我们通过新方法扩展了该包络，以改善其在部署场景中的应用效果，包括降低计算开销和抑制估计噪声。最后，我们展示了该方法在自动驾驶中多种潜在部署偏移场景（如夜间、雨天或雪天领域的转换）中的适用性。总体而言，我们的方法在部署场景中展现了巨大潜力，能够通过不确定性实现运行设计域识别，从而支持防御性感知、安全状态触发、预警通知以及感知栈的测试、开发与自适应反馈。