Andreas Wilde

Probabilistic approach for modeling and identifying driving situations

Intelligent vehicles need increasing knowledge about both their own state and the driving environment. In this work a novel method for interpreting this information by a reliable detection of relevant driving situations and driving maneuvers is proposed. The information of a situation or maneuver is extracted and hence provided for subsequent processing in the applications. As a result of different situation perception and maneuver realization of the drivers, the selected method is based on probabilistic decisions. Furthermore the inaccuracy of this decision is estimated by the inaccuracies of the sensor measurements. This value can be seen as quality measure of the probabilistic situation and maneuver detection. In addition the model allows to derivate requirements on the sensors, while determining a relevance ranking of the separate sensor information regarding the situation decision.

Driving situation and driving style dependent charging strategy in hybrid electric vehicles

Adaptive and situation-dependent charging strategies of batteries in hybrid electric vehicles aim to resolve the conflict between high efficiency and optimal driving performance. By using inputs from devices such as navigation system, radar and camera, as well as from standard sensors, driving situations challenging the electrical energy storage device are identified and predicted in real time, onboard the vehicle. BMW provides an overview of energy potentials of such adaptive energy functions and presents a method for driving situation classification using fuzzy probabilistic networks.

Fahrstil- und fahrsituations-abhängige Ladestrategie bei Hybridfahrzeugen

Adaptive und fahrsituationsabhangige Ladestrategien fur Batterien in Hybridfahrzeugen helfen, den Ziel konflikt zwischen hoher Effizienz und optimaler Fahrleistung zu minimieren. In Echtzeit wird anhand von Informationen aus Navigationssystem, Abstandsradar, Kamera und ubrigen Sensoren eine Kennzahl fur die Wahrscheinlichkeit einer Fahrsituation beziehungsweise den Fahrstil ermittelt. BMW gibt einen Uberblick uber simulationsgestutzt gewonnene, energetische Potenziale derartiger Energiefunktionen — und stellt eine Methode zur Fahrsituationsklassifikation unter Nutzung von fuzzy-probabilistischen Netzen vor.