PRIDE (PRediction In Dynamic Environments) is a framework that provides an autonomous vehicle's planning system with information that it needs to perform path planning in the presence of moving objects. The underlying concept is based upon a multi-resolutional, hierarchical approach that incorporates multiple prediction algorithms into a single, unifying framework. This framework supports the prediction of the future location of moving objects at various levels of resolution, thus providing prediction information at the frequency and level of abstraction necessary for planners at different levels within the hierarchy.This paper presents the chronology of the development of the PRIDE framework, starting back in 2003 when the initial concept called Moving Object Representation, Prediction, and Planning System (MORPPS) was first introduced using a Kalman filter-based prediction approach.In 2004, we started using the AutoSim simulation package to provide higher resolution simulations of moving objects and on-road driving. We also introduced a second set of prediction algorithms that predicted at longer timeframes (seconds into the future as opposed to tenths of seconds).The PRIDE framework appeared in 2005 and looked at using the outputs of the two prediction approaches to strengthen/weaken the results of the other. PRIDE was also applied to simulate realistic traffic patterns during on-road driving by using the longer-term prediction algorithms to control individual vehicles on a crowded roadway.
Proceedings Title: Proceedings of PerMIS | 2007 |
Conference Dates: August 28-30, 2007
Conference Location: Gaithersburg, MD
Conference Title: Performance Metrics for Intelligent Systems (PerMIS) 2007
Pub Type: Conferences
aggressivity, autosim, long-term predicition, moving object prediction, OTBSAF, PRIDE, short-term predicition, traffic simulation