Currently available driver assistance systems (i) warn the driver based on vehicle state sensors (e.g., door open, outside temperature near or below the freezing point), (ii) offer route guidance information (navigation systems based on GPS and digital road maps), or—in some critical situations—(iii) even actively influence vehicle handling under carefully delimited conditions (anti-blocking-system, electronic-stability-program).

This contribution reports about investigations to combine passive GPS- and map-based route guidance with model-based machine vision in order to automatically assess or even execute driving maneuvers in inner-city traffic situations. Information provided by todays route guidance systems is treated as a generic description of lane structure. The schematic description of lane structures extractable from commercially available standard digital maps is automatically instantiated by a machine vision approach which interprets video image sequences recorded by cameras from within a driving vehicle. The resulting model of the lane structure in front of the vehicle is subsequently exploited in order to control vehicle maneuvers in real-time as a proof of principal system competences. The machine-vision-based execution of driving maneuvers can at any time be overridden by the driver.

Towards Active Machine-Vision-Based Driver Assistance for Urban Areas

IDRES: A rule-based system for driving situation recognition with uncertainty management

Driving situation recognition with uncertainty management and rule-based systems

Driving in car-following situations consists in adapting to traffic constraints and variations, and detecting "critical" variations, i.e. those which demand regulating action to avoid a collision. The purpose of this research work is to find out how the driver manages this type of road situation and how he regulates his speed and controls his distance vis-a-vis other vehicles, applying strategies that need to be identified. The methodology used entails making observations of drivers' behaviour from within a specially equipped vehicle during an actual journey on an urban motorway. To complement these observations, in-depth interviews (using assisted subsequent verbalization techniques) were conducted with the drivers. Two groups of experienced and novice drivers participated in the study. In this paper, a synthesis is presented of the main results of analysis of observational and verbal data and the contribution of an in-depth investigation of drivers' "effective" practices in the complexity of real driving situations is discussed in order to design appropriate drivers' support systems as well as to evaluate their impact on drivers' activity. (A) For the covering abstract, see IRRD 887275.

Critical car-following when driving on an urban motorway: analyses of the situational demands and driver's activity in real driving conditions

This article deals with how metaknowledge can improve rule-based system and presents a new Reflexive System Inference Engine (RSIE) which not only enables the activation of rules, making it belong to systems managing metaknowledge. The experimentation section shows a rule-based system named IDRES with a structure which has been modified to use metaknowledge.

RSIE : a inference engine for reflexive systems

This paper presents the French CASSICE project developed by five academic laboratories. The aim of this project is to develop a system enabling the acquisition of the driving information to be automated and to used as an aid for the ex-post analysis of road situations and driver behaviours. This project needs a tight collaboration between the psychologists an engineers. The system is based on the development of an experimental vehicle including a multi-sensors based electronic embedded system. Then, a time stamped database is built in order to provide a continuous detailed description of the various road situations encountered throughout the motorway journey and of drivers' behaviour in relation to those situations.

M. Rombaut

Papers

CASSICE: symbolic characterization of driving situation