PRORETA 3: An Integrated Approach to Collision Avoidance and Vehicle Automation

Abstract

The article describes first results of the research project PRORETA 3 that aims at the development of an integral driver assistance system for collision avoidance and automated vehicle guidance based on a modular system architecture. For this purpose, relevant information is extracted from a dense environment model and fed into a potential field-based trajectory planner that calculates reference signals for underlying vehicle controllers. In addition, the driver is supported by a human-machine interface. Zusammenfassung Der Beitrag beschreibt erste Ergebnisse des Forschungsprojektes PRORETA 3, das die Entwicklung eines integralen Fahrerassistenzsystems zur Kollisionsvermeidung und automatisierten Fahrzeugführung auf Basis einer modularen Systemarchitektur anstrebt. Hierzu werden relevante Informationen aus einem dichten Umfeldmodell extrahiert und in einem potentialfeldbasierten Trajektorienplaner verarbeitet, der Führungsgrößen für unterlagerte Fahrzeugregler generiert. Zusätzlich unterstützt eine Mensch-Maschine-Schnittstelle den Fahrer zielgerichtet bei der Fahrzeugführung.

Bayesian environment representation, prediction, and criticality assessment for driver assistance systems

“…In this context, the term mode probability refers to the probability of the event that a hypothesized model matches the true behavior pattern or mode of a system [153]. We consider the j-th model of a fixed model set 25 …”

“…The DBN of this jump Markov system 26 is shown in Figure 3.4. 25 If even the number of models is allowed to vary over time, it is termed a Variable Structure Multiple Model (VSMM) [150,153]. 26 We consider a so- .…”

“…In the field of intelligent vehicles, it is a known fact [92] that solely sparse object-based environment models -as used in today's adaptive cruise control or emergency braking systems -are not sufficient for the realization of future ADAS such as Collision Avoidance Systems (CAS) in arbitrary environments [25] or general lateral vehicle guidance systems, e.g. in narrow inner-city roads [172], in construction sites [155], or with respect to arbitrary elevated objects [25].…”

“…in narrow inner-city roads [172], in construction sites [155], or with respect to arbitrary elevated objects [25]. However, an established interface for the required dense environment models for these near-future ADAS functions does not exist [92], and there is no clear consensus which representation is the most suitable.…”

“…• for potential field-based safety trajectory planning and lateral vehicle guidance with respect to elevated objects in PRORETA 3 [25,56,219,220,274,275], see Chapter 7.…”