… aids, autonomous driving vehicles, or last-mile delivery agents. In most of these applications,
as robots navigate closely around humans, it is essential that they follow the navigational …

… The arrows in the visualization indicate our model’s predicted motion vectors, and the color
corresponds to the magnitude, as indicated by the color bar in (g). Vectors beyond the range …

… In this paper, we investigate how autonomous driving marries … major fields of self-driving
technologies, such as perception, … human motion prediction and vehicle behaviour prediction […

… We believe it is because that the motion pattern of pedestrians are more flexible than vehicles
and bikes with non-holonomic constraint. Another remarkable finding is that simple model …

… autonomous vehicles should comply with rules to a certain extent, and it is difficult to find
control inputs for autonomous … approach for the autonomous driving problem. We combine the …

… in common use for autonomous driving and DST basic notions. This is followed by the
proposed model for lateral and longitudinal relative motion of surrounding moving objects. The …

… imitation learning for motion prediction problem in autonomous driving, especially in multi-…
baseline methods in the simulation of multi-agent driving and is very efficient in term of GPU …

… To our knowledge, this work provides the first learning paradigm that is able to perform
pillar motion prediction in a fully self-supervised framework. We propose novel self-supervisory …

… evaluating motion prediction with planning in the context of autonomous driving. The main
goal is to create a safe and efficient driving plan based on the prediction of traffic participants’ …

… In this work, we study two learning and prediction paradigms based on trajectory and direct
control, respectively, for end-to-end autonomous driving. We propose a unified framework …