The local road network information is essential for autonomous navigation. This information
is commonly obtained from offline HD-Maps in terms of lane graphs. However, the local road …

Accurate trajectory prediction is crucial for ensuring safe and efficient autonomous driving.
However, most existing methods overlook complex interactions between traffic participants …

Motion forecasting is crucial for improving the safety and efficiency of autonomous driving.
However, fore-casting the future motion of surrounding moving agents (eg pedestrians and …

针对目前车辆轨迹预测难点, 对车辆轨迹预测方法的分类和研究现状进行综述.
根据模型实现预测时域的不同, 将现有算法分为短时域和长时域的车辆轨迹预测方法; …

Autonomous systems strongly rely on computer vision to build a comprehensive model for
understanding the environment they are embedded in. This task needs to be solved on …

In this thesis, online understanding of the traffic scene using onboard sensors is addressed.
To this end, several approaches for direct extraction of centerline based lane graphs are …