Artificial Intelligence (AI) shows promising applications for the perception and planning tasks in autonomous driving (AD) due to its superior performance compared to conventional methods. However, inscrutable AI systems exacerbate the existing challenge of safety assurance of AD. One way to mitigate this challenge is to utilize explainable AI (XAI) techniques. To this end, we present the first comprehensive systematic literature review of explainable methods for safe and trustworthy AD. We begin by analyzing the requirements for AI in the context of AD, focusing on three key aspects: data, model, and agency. We find that XAI is fundamental to meeting these requirements. Based on this, we explain the sources of explanations in AI and describe a taxonomy of XAI. We then identify five key contributions of XAI for safe and trustworthy AI in AD, which are interpretable design, interpretable surrogate models, interpretable monitoring, auxiliary explanations, and interpretable validation. Finally, we propose a modular framework called SafeX to integrate these contributions, enabling explanation delivery to users while simultaneously ensuring the safety of AI models.

翻译：人工智能（AI）因其相较于传统方法的优越性能，在自动驾驶（AD）的感知与规划任务中展现出广阔的应用前景。然而，难以理解的AI系统加剧了自动驾驶安全保证这一固有挑战。利用可解释人工智能（XAI）技术是缓解这一挑战的途径之一。为此，我们首次对面向安全可信自动驾驶的可解释方法进行了全面系统的文献综述。我们首先分析了自动驾驶背景下对AI的需求，聚焦于数据、模型和智能体三个关键方面。我们发现，XAI是满足这些需求的基础。基于此，我们阐释了AI中解释的来源，并描述了XAI的分类体系。随后，我们识别出XAI为自动驾驶中安全可信AI做出的五项关键贡献，即可解释设计、可解释代理模型、可解释监控、辅助解释以及可解释验证。最后，我们提出了一个名为SafeX的模块化框架来整合这些贡献，使其能够在向用户提供解释的同时，确保AI模型的安全性。