Trajectory-Prediction with Vision: A Survey

Abstract

To plan a safe and efficient route, an autonomous vehicle should anticipate the future trajectories of other agents around it. Trajectory prediction is an extremely challenging task recently gaining much attention in the autonomous vehicle research community. Trajectory prediction forecasts the future state of all the dynamic agents in the scene, given their current and past states. A good prediction model can prevent collisions on the road, hence the ultimate goal for autonomous vehicles: Collision rate: collisions per Million miles. This paper aims to provide an overview of the field trajectory-prediction. We categorize the relevant algorithms into different classes so that researchers can follow through the trends in the trajectory-prediction research field. Moreover, we also touch upon the background knowledge required to formulate a trajectory-prediction problem.