LIDAR sensors are usually used to provide autonomous vehicles with three-dimensional representations of their environment. In ideal conditions, geometrical models could detect the road in LIDAR scans, at the cost of a manual tuning of numerical constraints, and a lack of flexibility. We instead propose an evidential pipeline, to accumulate road detection results obtained from neural networks. First, we introduce RoadSeg, a new convolutional architecture that is optimized for road detection in LIDAR scans. RoadSeg is used to classify individual LIDAR points as either belonging to the road, or not. Yet, such point-level classification results need to be converted into a dense representation, that can be used by an autonomous vehicle. We thus second present an evidential road mapping algorithm, that fuses consecutive road detection results. We benefitted from a reinterpretation of logistic classifiers, which can be seen as generating a collection of simple evidential mass functions. An evidential grid map that depicts the road can then be obtained, by projecting the classification results from RoadSeg into grid cells, and by handling moving objects via conflict analysis. The system was trained and evaluated on real-life data. A python implementation maintains a 10 Hz framerate. Since road labels were needed for training, a soft labeling procedure, relying lane-level HD maps, was used to generate coarse training and validation sets. An additional test set was manually labeled for evaluation purposes. So as to reach satisfactory results, the system fuses road detection results obtained from three variants of RoadSeg, processing different LIDAR features.

中文翻译：

---

神经网络融合，用于基于 LIDAR 的证据道路映射

LIDAR 传感器通常用于为自动驾驶汽车提供其环境的三维表示。在理想条件下，几何模型可以在激光雷达扫描中检测道路，代价是手动调整数值约束，并且缺乏灵活性。相反，我们提出了一个证据管道，以积累从神经网络获得的道路检测结果。首先，我们介绍 RoadSeg，这是一种新的卷积架构，针对激光雷达扫描中的道路检测进行了优化。RoadSeg 用于将单个 LIDAR 点分类为属于道路或不属于道路。然而，这样的点级分类结果需要转换为密集表示，供自动驾驶汽车使用。因此，我们第二次提出了一种证据道路映射算法，该算法融合了连续道路检测结果。我们受益于对逻辑分类器的重新解释，可以将其视为生成简单证据质量函数的集合。然后，通过将 RoadSeg 的分类结果投影到网格单元中，并通过冲突分析处理移动对象，可以获得描绘道路的证据网格图。该系统接受了现实生活数据的训练和评估。python 实现保持 10 Hz 帧速率。由于训练需要道路标签，因此使用依赖车道级高清地图的软标签程序来生成粗略的训练和验证集。出于评估目的，手动标记了一个额外的测试集。为了达到满意的结果，系统融合了从 RoadSeg 的三个变体获得的道路检测结果，处理不同的 LIDAR 特征。