ChangeandMergeDriverAssistance.PDF

This article has been accepted for inclusion in a future issue of this journal. Content is final as presented, with the exception of pagination. IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 1 Dynamic Probabilistic Drivability Maps for Lane Change and Merge Driver Assistance Sayanan Sivaraman, Member, IEEE , and Mohan Manubhai Trivedi, Fellow, IEEE Abstract—In this paper, we present a novel probabilistic com- accelerate up to highway speeds. A typical merge scenario is pact representation of the on-road environment, i.e., the dynamic shown in Fig. 1(c). probabilistic drivability map (DPDM), and demonstrate its utility In recent years, there has been great progress in sensing for predictive lane change and merge (LCM) driver assistance dur- ing highway and urban driving. The DPDM is a flexible represen- and computation for intelligent vehicles. Sensors have become tation and readily accepts data from a variety of sensor modalities higher in fidelity and cheaper over time. Computation has to represent the on-road environment as a spatially coded data become cheaper and faster, whereas the advent of multicore structure, encapsulating spatial, dynamic, and legal information. architectures and graphical processing units (GPUs) allows Using the DPDM, we develop a general predictive system for for parallel processing. Research efforts that utilize intelligent LCMs. We formulate the LCM assistance system to solve for the minimum-cost solution to merge or change lanes, which is vehicles, equipped with advanced sensing and computing tech- solved efficiently using dynamic programming over th