Suche nach „[S.] [Kraust]“ hat 1 Publikationen gefundenSuchergebnis als PDF
MobilElektrotechnik und Medientechnik
Beitrag (Sammelband oder Tagungsband)
Intention-Based Prediction for Pedestrians and Vehicles in Unstructured Environments
Motion prediction for holonomic objects in unstructured environments is an ambitious task due to their high freedom of movement compared with non-holonomic objects. In this paper, we present a method for inferring the future goal of holonomic objects by a heuristic generation of target points (tp) and following discriminating decision making. The target points are generated, in a manner that covers the most common motion hypotheses like following or staying, safety relevant motion hypotheses like crossing future ego trajectories or the movement to special points of interest, e.g. gained from a map. Subsequently, for each considered object a trajectory to the inferred target point will be planned. Finally, the uncertainty of the trajectory is estimated by applying a Kalman Filter with a dynamically adjusted process noise matrix. An additional benefit of this concept is its ability to cope with a different quality of context knowledge, so it can produce sound results even at poor structured environments.