Abstract: Integration of UAVs with Air Traffic Control (ATC) is a world wide problem. ATC is already troubled by capacity
problems due to a vast amount of air traffic. In the future when large numbers of Unmanned Aerial Vehicles
(UAVs) will participate in the same airspace, the situation cannot afford to have UAVs that need special attention.
Regulations for UAV flights in civil airspace are still being developed but it is expected that authorities will require
UAVs to operate ‘like manned aircraft’. The implication is that UAVs need to become full participants of a complex
socio-technical environment and need to generate ‘man like’ decisions and behavior. In order to deal with the
complexity a novel approach to developing UAV autonomy is needed, aimed to create an environment that fosters
shared situationawareness between the UAVs, pilots and controllers. The underlying principle is to develop an
understanding of the work domain that can be shared between people and UAVs. A powerful framework to
represent the meaningful structure of the environment is Rasmussen’s abstraction hierarchy. This paper proposes
that autonomous UAVs can base their reasoning, decisions and actions on the abstraction hierarchy framework and
communicate about their goals and intentions with human operators. It is hypothesized that the properties of the
framework can create ‘shared situationawareness’ between the artificial and human operators despite the
differences in their internal workings.
Abstract: The investigations presented in this thesis are part of the 'Integrated Collaborative Information Systems' (ICIS) project, focussing on the 'Enhanced SituationAwareness' (ESA). As a partner in ths project, we investigated the feasibility of using morphologicallt elaborate model neurons to enhance robustness and adaptivity in robotic systems.
Abstract: French coastguard missions have become increasingly varied implying new challenges such as the reduction of the decision cycle and the expansion of available information. Thus, it involves new needs for enhanced decision support. An efficient situationawareness system has to quickly detect and identify suspicious boats. The efficiency of such a system relies on a reliable sensor fusion since a coastguard uses sensors to achieve his mission. We present an innovative approach based on multi-agent negotiation to fuse classifiers, benefiting from the efficiency of existing classification tools and from the flexibility and reliability of a multi-agent system to exploit distributed data across dispersed sources. We developed a first prototype using a basic negotiation protocol in order to validate the feasibility and the interest of our approach. The results obtained are promising and encourage us to continue on this way.
Abstract: When we talk about improving Information Systems for Crisis Response and Management, we must consider at least two sorts of problems to solve: the processing of human provided information (perception and knowledge) in combination with other sensor information and the human processing of sensor based information (for situationawareness and decision making). As an illustration, two examples of research work that is done at the D-CIS lab in Delft is presented here. The first example is about Distributed Perception Networks in disaster management and the second example is about cognitive performance factors in decision making (in crisis situations).
Abstract: The MOSAIC project aims at enhanced situationawareness and reduced information overload to public safety officers (police, fire brigade, medical transport) in a complex safety incident.
In this first MOSAIC indicative experiment, a realistic safety incident, a ship collision with many persons and poisonous gas involved, was simulated by messages on this incident. These messages correspond to usual messages sent to the local police commander at the location of incident.
In the experiment, the original message set (Set-0) was reduced in consecutive ways.
In Set-1 messages on victims and events related to the safety incident were combined.
In Set-3 only information pertaining to operational police tasks remained (all information on the informative police task was removed).
The normal operational background task of the Control and Command Room (CCR) was simulated by a computer game.
The effects of the information reduction on situationawareness and information overload were measured by a questionnaire with questions on the situation, an open evaluation, and background task performance.
Eighteen police officers participated in the experiment. The results showed that removal of messages containing information that was sent before reduces the information overload that is experienced. Aggregating numbers of victims and certain types of events is a most effective way to decrease the number of messages while improving situationawareness. Aggregating geographical data by plotting was, unexpectedly not effective; training beforehand might have improved this.
To conclude, reduction of the number of messages proved to be effective in improving information processing of police officers.
Abstract: Designers of autonomous systems, embodied in an uncertain environment, have the ten-
dency to build up a world model from everything that can be perceived. In contrast to this view,
psychological researchers find for humans a selective interpretation of a scene, with phenom-
ena like inattentional blindness. Objects remain unseen if they are not central to the current
behavior, even while they are clearly within view. Previous research in the Dutch Aibo Team
has proven that also for robots behavior-specific image processing can be very beneficial. In
this article we design an experiment where we can not only indicate the appropriate moments
to limit the perception to the objects relevant to the task, but also indicate the appropriate
moments to release those limitations and to increase the overall situationawareness.
Abstract: This paper describes the optimization of traffic light controllers using a model-based reinforcement learning approach. Traffic lights are optimized using mostly local, low-level information, but some high-level information concerning the general traffic situation at neighboring traffic junctions is take into account, enhancing situationawareness and improving decision making. We show, using experiments performed with a traffic simulator, that this approach outperforms existing methods.