Galia Weidl

Object-Oriented Bayesian Networks for Detection of Lane Change Maneuvers

This article introduces a novel approach towards the recognition of typical driving maneuvers in structured highway scenarios and shows some key benefits of traffic scene modeling with object-oriented Bayesian networks (OOBNs). The approach exploits the advantages of an introduced lane-related coordinate system together with individual occupancy schedule grids for all modeled vehicles. This combination allows an efficient classification of the existing vehicle-lane and vehicle- vehicle relations in traffic scenes and thus substantially improves the understanding of complex traffic scenes. Probabilities and variances within the network are propagated systematically which results in probabilistic sets of the modeled driving maneuvers. Using this generic approach, the network is able to classify a total of 27 driving maneuvers including merging and object following.

Advisory warnings based on cooperative perception

The Ko-PER (cooperative perception) research project aims at improvements of active traffic safety through cooperative perception systems. Within the project a prototype of a cooperative warning system was realized. This system provides early advisory warnings which are especially useful in critical situations with occluded conflict partners. The development process was accompanied by a series of driving simulator studies to determine both the potential to reduce traffic conflicts and important design characteristics of early advisory warning signals. The most important details of the prototype systems components inter-vehicle information-fusion and situation analysis are described and the achieved warning timings are compared to the results of the driving simulator studies.

Overall Probabilistic Framework for Modeling and Analysis of Intersection Situations

We propose a system design for preventive traffic safety in general intersection situations involving all present traffic participants (vehicles and vulnerable road users) in the context of their environment and traffic rules. It exploits the developed overall probabilistic framework for modeling and analysis of intersection situations under uncertainties in the scene, in measured data or in communicated information. It proposes OOBN modeling for the cognitive assessment of potential and real danger in intersection situations and presents schematically an algorithm for multistage cognitive situation assessment. A concept for the interaction between situation assessment and the proposed Proactive coaching Safety Assistance System (PaSAS) is outlined. The assessment of danger in a situation development serves as a filter for the output and intensity of HMI-signals for directing driver’s attention to essentials.

Optimizing Bayesian networks for recognition of driving maneuvers to meet the automotive requirements

An Object Oriented Bayesian Network for recognition of maneuver in highway traffic has demonstrated an acceptably high recognition performance on a prototype car with a Linux PC having an i7 processor. This paper is focusing on keeping the high recognition performance of the original OOBN, while evaluating alternative modelling techniques and their impact on the memory and time requirements of an ECU-processor for automotive applications. New challenges are faced, when the prediction horizon is to be further extended.

Situation Awareness and Early Recognition of Traffic Maneuvers

We outline the challenges of situation awareness with early and accurate recognition of traffic maneuvers and how to assess them. This includes also an overview of the available data and derived situation features, handling of data uncertainties, modelling and the approach for maneuver recognition. An efficient and effective solution, meeting the automotive requirements, is successfully deployed and tested on a prototype car. Test driving results show that earlier recognition of intended maneuver is feasible on average 1 second (and up to 6.72 s) before the actual lane marking crossing. The even earlier maneuver recognition is dependent on the earlier recognition of surrounding vehicles.

Early Recognition of Maneuvers in Highway Traffic

This paper presents an application of Bayesian networks where early recognition of traffic maneuver intention is achieved using features of lane change, representing the relative dynamics between vehicles on the same lane and the free space to neighbor vehicles back and front on the target lane. The classifiers have been deployed on the automotive target platform, which has severe constraints on time and space performance of the system. The test driving has been performed with encouraging results. Even earlier recognition is possible by considering the trend development of features, characterizing the dynamic driving process. The preliminary test results confirm feasibility.