@inproceedings{WeidlMadsenTereshchenkoetal.2015, author = {Weidl, Galia and Madsen, Anders L. and Tereshchenko, Viacheslav and Kaspar, Dietmar and Breuel, Gabi}, title = {Early Recognition of Maneuvers in Highway Traffic}, series = {European Conference on Symbolic and Quantitative Approaches to Reasoning and Uncertainty, July 2015}, booktitle = {European Conference on Symbolic and Quantitative Approaches to Reasoning and Uncertainty, July 2015}, doi = {10.1007/978-3-319-20807-7_48}, year = {2015}, abstract = {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.}, subject = {Fahrerassistenzsystem}, language = {en} } @inproceedings{WeidlMadsenKasparetal.2014, author = {Weidl, Galia and Madsen, Anders L. and Kaspar, Dietmar and Breuel, Gabi}, title = {Optimizing Bayesian networks for recognition of driving maneuvers to meet the automotive requirements}, series = {The 2014 IEEE Multi-Conference on Systems and Control (MSC 2014)}, booktitle = {The 2014 IEEE Multi-Conference on Systems and Control (MSC 2014)}, doi = {10.1109/ISIC.2014.6967630}, year = {2014}, abstract = {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.}, subject = {Fahrerassistenzsystem}, language = {en} } @inproceedings{SeeligerWeidlPetrichetal.2014, author = {Seeliger, Florian and Weidl, Galia and Petrich, Dominik and Naujoks, Frederik and Breuel, Gabi and Neukum, Alexandra and Dietmayer, Klaus}, title = {Advisory warnings based on cooperative perception}, series = {IEEE Intelligent Vehicles Symposium Proceedings, June 2014}, booktitle = {IEEE Intelligent Vehicles Symposium Proceedings, June 2014}, doi = {10.1109/IVS.2014.6856479}, year = {2014}, abstract = {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 system's 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.}, subject = {Fahrerassistenzsystem}, language = {en} } @inproceedings{WeidlSinghalPetrichetal.2013, author = {Weidl, Galia and Singhal, Virat and Petrich, Dominik and Kaspar, Dietmar and Wedel, Andreas and Breuel, Gabi}, title = {Collision Risk Prediction and Warning at Road Intersections Using an Object Oriented Bayesian Network}, series = {5th International Conference Automotive User Interfaces and Interactive Vehicular Applications (Automotive UI,13), Oct.28-30, 2013}, booktitle = {5th International Conference Automotive User Interfaces and Interactive Vehicular Applications (Automotive UI,13), Oct.28-30, 2013}, doi = {10.1145/2516540.2516577}, year = {2013}, abstract = {This paper describes a novel approach to situation analysis at intersections using object-oriented Bayesian networks. The Bayesian network infers the collision probability for all vehicles approaching the intersection, while taking into account traffic rules, the digital street map, and the sensors' uncertainties. The environment perception is fused from communicated data, vehicles local perception and self-localization. Thus, a cooperatively validated set of data is obtained to characterize all objects involved in a situation (resolving occlusions). The system is tested with data, acquired by vehicles with heterogenic equipment (without/with perception). In a first step the probabilistic mapping of a vehicle onto a fixed set of traffic lanes and forward motion predictions is introduced. Second, criticality measures are evaluated for these motion predictions to infer the collision probability. In our test vehicle this probability is then used to warn the driver of a possible hazardous situation. It serves as a likelihood alarm parameter for deciding the intensity of HMI acoustic signals to direct the driver's attention. First results in various simulated and live real-time scenarios show, that a collision can be predicted up to two seconds before a possible impact by applying the developed Bayesian network. The extension of this network to further situation features is the content of ongoing research.}, subject = {Fahrerassistenzsystem}, language = {en} } @inproceedings{KasparWeidlDangetal.2011, author = {Kaspar, Dietmar and Weidl, Galia and Dang, Thao and Breuel, Gabi and Tamke, Andreas and Rosenstiel, Wolfgang}, title = {Erkennung von Fahrman{\"o}vern mit objektorientierten Bayes-Netzen}, series = {7. Workshop. Fahrerassistenzsysteme. FAS2011}, booktitle = {7. Workshop. Fahrerassistenzsysteme. FAS2011}, year = {2011}, abstract = {In diesem Artikel wird ein Ansatz zur Erkennung von Spurwechselman{\"o}vern mit Hilfe von objekt-orientierten Bayes Netzen beschrieben. Dieser Ansatz ist eine Erweiterung von Grundlagenarbeiten zur Einscherererkennung. Zun{\"a}chst werden die zur Erkennung von Spurwechselvorg{\"a}ngen erforderlichen Fahrsituationsmerkmale vorgestellt. Darauf aufbauend wird das entwickelte objekt-orientierte Bayes Netz zur Modellierung der Spurwechsel erl{\"a}utert. Dabei wird ein Spurwechsel als eine Beziehung zwischen zwei Fahrzeugen betrachtet. Dabei kann ein Fahrzeug in der Spur bleiben, die Spur nach links oder nach rechts wechseln. Durch die Kombination der M{\"o}glichkeiten der beiden Fahrzeuge entstehen 9 Klassen. Aus den relativen Positionen der Fahrzeuge ergeben sich aus den 9 Situationsklassen 27 m{\"o}gliche Spurwechselman{\"o}ver. Dabei ist das Einschervorgang ein Sonderfall der modellierten Fahrman{\"o}ver.}, subject = {Fahrerassistenzsystem}, language = {de} }