… and motion information for motion planning. … motion prediction based on BEV maps. MotionNet
is bounding-box free and can provide complementary information for autonomous driving; …

… Specifically, we identify and classify motion prediction literature for two road user classes ie
… and vehicle motion prediction literature and is built on three dimensions ie motion modelling …

… Alternative directions for future research could explore applications of WIMP beyond
autonomous driving, perhaps for prediction of pedestrian trajectories or human actions; we will …

… to predict future motion of traffic actors. Comprehensive overview of the topic can be found
in [30, 47]. Here, we review literature from the perspective of autonomous driving domain. We …

… to model the complex motion prediction task. Our main contributions are summarized as: •
We propose a safety-aware motion prediction task for autonomous driving. The task predicts …

… motion prediction are essential components for completely replacing human drivers and for
enabling highly and fully automated driving … scenarios, autonomous driving software must act …

… In this work, we propose a motion prediction scheme based … The proposed scheme is
capable of predicting collision-free, … behavior most drivers exhibit in typical driving scenarios, ie, …

… In this study, a motion planning framework based on target motion prediction for autonomous
driving at uncontrolled intersections is developed. The key feature of the uncontrolled …

… prediction … of motion prediction, we propose a multimodal attention Transformer encoder,
which modifies the multihead attention mechanism to multi-modal attention, and each predicted …

Predicting the future states of surrounding traffic participants and … for autonomous vehicles
(AVs). There are two major issues with the current autonomous driving system: the prediction …