论文标题
使用语义图和注意力学习准确和类似人类的驾驶
Learning Accurate and Human-Like Driving using Semantic Maps and Attention
论文作者
论文摘要
本文研究了如何改善端到端驾驶模型以更准确和类似于人类。为了解决第一个问题，我们从这里利用语义和视觉图，并增加现有的驱动器360数据集。这些地图用于促进分割置信面罩的注意机制，从而将网络集中在图像中的语义类别上，这对于当前的驾驶情况很重要。使用对抗性学习可以实现类似人类的驾驶，不仅通过将模仿损失相对于人类驾驶员而最小化，而且通过进一步定义歧视者，从而迫使驱动模型产生类似人类的动作序列。我们的模型在此处的Drive360 +数据集上进行了训练和评估，该数据集具有60小时3000公里的现实驾驶数据。广泛的实验表明，我们的驾驶模型比以前的方法更准确，并且行为更像人性化。
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.
