This paper investigates how end-to-end driving models can be improved to drive more accurately and human-like. To tackle the first issue we exploit semantic and visual maps from HERE Technologies and augment the existing Drive360 dataset with such. The maps are used in an attention mechanism that promotes segmentation confidence masks, thus focusing the network on semantic classes in the image that are important for the current driving situation. Human-like driving is achieved using adversarial learning, by not only minimizing the imitation loss with respect to the human driver but by further defining a discriminator, that forces the driving model to produce action sequences that are human-like. Our models are trained and evaluated on the Drive360 + HERE dataset, which features 60 hours and 3000 km of real-world driving data. Extensive experiments show that our driving models are more accurate and behave more human-like than previous methods.

中文翻译：

---

使用语义地图和注意力学习准确和类人驾驶

本文研究了如何改进端到端驾驶模型以实现更准确和更人性化的驾驶。为了解决第一个问题，我们利用来自 HERE Technologies 的语义和视觉地图，并使用此类扩充现有的 Drive360 数据集。这些地图用于提高分割置信度掩码的注意力机制，从而将网络集中在图像中对当前驾驶情况很重要的语义类别上。类人驾驶是使用对抗性学习实现的，不仅通过最大限度地减少对人类驾驶员的模仿损失，而且通过进一步定义鉴别器，迫使驾驶模型产生类人的动作序列。我们的模型在 Drive360 + HERE 数据集上进行了训练和评估，该数据集具有 60 小时和 3000 公里的真实驾驶数据。