SPOT: A tool for set-based prediction of traffic participants

Abstract

Predicting the movement of other traffic participants is an integral part in the motion planning of most automated road vehicles. While simple predictions, e.g. based on assuming constant velocity, may suffice for deciding a driving strategy, predicting the set of all possible behaviors is required to ensure safe motion plans. In this work, we propose a novel tool for the latter problem based on reachability analysis: Set-Based Prediction Of Traffic Participants (SPOT). Our tool can predict the future occupancy of other traffic participants, including all possible maneuvers (e.g. full acceleration, full braking, and arbitrary lane changes), by considering physical constraints and assuming that the traffic participants abide by the traffic rules. However, we remove assumptions for each traffic participant individually as soon as a violation of a traffic rule is detected. Removal of assumptions automatically results in larger occupancies and thus a smaller drivable area for the ego vehicle, ensuring that the ego vehicle does not cause a collision during the time horizon of the prediction. Experimental results show that we obtain the set of future occupancies within a fraction of the prediction horizon. Our tool is available at spot.in.tum.de.