通过学习奖励权重，让自动驾驶车辆行为解释更可信。
Generating Causal Explanations of Vehicular Agent Behavioural Interactions with Learnt Reward Profiles
- 从真实驾驶数据中学习代理的奖励权重
- 在三个数据集上验证，解释准确率优于现有方法
- 适合关注自动驾驶可解释性的研究者与工程师
透明性和可解释性是负责任自动驾驶车辆在与人类交互时必须具备的重要特性，而因果推理为此提供了坚实基础。然而，即便假设代理以最大化某种奖励为目标，若无法捕捉代理所重视的内容，也难以进行准确的因果推断。因此，本工作旨在学习代理的奖励度量权重，使得其交互行为能够被因果地解释。我们在三个真实世界驾驶数据集上对方法进行了定量和定性验证，结果表明该方法在功能上优于以往方法，并在各项评估指标上表现具有竞争力。
原文摘要 · Abstract (English)
Transparency and explainability are important features that responsible autonomous vehicles should possess, particularly when interacting with humans, and causal reasoning offers a strong basis to provide these qualities. However, even if one assumes agents act to maximise some concept of reward, it is difficult to make accurate causal inferences of agent planning without capturing what is of importance to the agent. Thus our work aims to learn a weighting of reward metrics for agents such that explanations for agent interactions can be causally inferred. We validate our approach quantitatively and qualitatively across three real-world driving datasets, demonstrating a functional improvement over previous methods and competitive performance across evaluation metrics.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。