Abstract: This paper presents a sampling strategy for
mobile gas sensors. Sampling points are selected using a modified artificial potential field (APF) approach, which balances multiple criteria to direct sensor measurements towards locations of high mean concentration, high concentration variance and areas for which the uncertainty about the gas distribution model is still large. By selecting in each step the most often suggested close-by easurement
location, the proposed approach introduces a locality constraint that allows planning suitable paths for mobile gas sensors. Initial results in simulation and in real-world experiments with a gas-sensitive micro-drone demonstrate the suitability of the proposed sampling strategy for gas distribution mapping and its use for gas source localization.
Abstract: This article investigates the prerequisites for a global exploration strategy in an unknown environment on a virtual disaster site. Assume that a robot equipped with a laser range scanner can build a detailed map of a previous unknown environment. The remaining question is how to use this information on this map for further exploration. On a map several interesting locations can be present where the exploration can be continued, referred as exploration frontiers. Typically, a greedy algorithm is used for the decision which frontier to explore next. Such a greedy algorithm only considers interesting locations locally, focused to reduce the movement costs. More sophisticated algorithms also take into account the information that can be gained along each frontier. This shifts the problem to estimate the amount of unexplored area behind the frontiers on the global map. Our algorithm exploits the long range of current laser scanners. Typically, during the previous exploration a small number of laser rays already passed the frontier, but this number is too low to have major impact on the generated map. Yet, the few rays through a frontier can be used to estimate the potential information gain from unexplored area beyond the frontier.
Abstract: In the crisis management problems, the coordination of emergency services and the evacuation of the injured people are a key issue in the response to a large scale crisis since lives are at stake. One can observe that the evacuation is based on three important elements: the examination and classification of the victims, the search for an allocation in the hospitals in the surrounding area and the transport. In this paper, we propose to assist the emergency call centre in the choice of a hospital for each injured man/woman according to his/her pathology, hospitals constraints and preferences, transportation and so on. The negotiation being a process by which a joint decision is made by two or more parties , we propose a negotiation based approach where agents are led to cooperate in order to achieve a global goal while trying to satisfy as best as possible individual preferences. This approach deals with more than two parties, each having its own decision criteria to evaluate an offer with multiple and dependent issues. Moreover, the preferences of our agents are modelled using a multi-criteria methodology and tools enabling us to take into account information about the improvements that can be done on a proposal, in order to help in quickening the search of a consensus between the agents. Therefore, we propose a negotiation protocol consisting in solving our decision problem using a MAS with a multi-criteria decision aiding modelling at the agent level and a cooperation-based multilateral multi-issue negotiation protocol. This protocol is studied under a non-cooperative approach and it is shown that it has subgame perfect equilibria, provided when agents behave rationally. Moreover, these equilibria converge to the usual maximum solution.
Abstract: In this paper we describe a new approach to make use of
a heterogeneous robot team for the RoboCup Rescue League Virtual
Robot competition. We will demonstrate coordinated action between a
flying and a ground robot. The flying robot is used for fast exploration
and allows the operator to find the places where victims are present in
the environment. Due to the fast aggregation of the location error in the
flying robot no precise location of the victim is known. It is the task of
the ground robot to autonomously go the point of interest and to get
an accurate location of the victim, which can be used by human rescue
workers to save the victim. The benefit of this approach is demonstrated
in a small number of experiments. By integrating the abilities of the two
robots the team’s performance is improved.
Abstract: The insertion of intelligent agents as active participants in an organization will
significantly alter team dynamics in general, and will transform standard command
teams into adaptive human – agent teams. In order to benefit from the adaptive
capabilities that this new type of organization promises, we need collaboration
schemes between human and artificial actors that harmonize with their respective
competences and demands. This paper explores various types of human – agent teams, with a focus on the issues
involved with designing dynamic task allocation and proper human – agent
collaboration. To this end, we introduce a taxonomy of human – agent team types and
elaborate on the issues and challenges involved with each type.
Abstract: The MOSAIC project aims at enhanced situation awareness 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 situation awareness 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 situation awareness. 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: In this paper time-augmented Petri nets are used to model people in the transit hall of an airport. Their behavior is strongly influenced
by an event with a clear deadline (their flight), but typically
there is so much time left that they linger and can be tempted to show
random other behaviors, often induced by the location (encountering a
coffee corner or a toilet). All behaviors are stochastic, but the firing rate
is made a function of both location and time. This framework allows to
show a rich set of behaviors; the diversity of the emergent behaviors is
initiated with probabilities from observations in an actual transit hall of
Abstract: We consider multiagent systems with stochastic non-linear dynamics in continuous space-time. We focus on systems of agents that aim to visit a number of given target locations at given points in time at minimal control cost. The online optimization of which agent has to visit which target requires the solution of the Hamilton-Jacobi-Bellman (HJB) equation, which is a non-linear partial differential equation (PDE). Under some conditions, the log-transform can be applied to turn the HJB equation into a linear PDE. We then show that the optimal solution in the multiagent scheduling problem can be expressed in closed form as a sum of single schedule solutions.
Abstract: This paper introduces a novel algorithm for approximate policy search in continuous-state discrete-action Markov decision processes (MDPs). Previous policy search approaches have typically used ad-hoc parameterizations developed for specific MDPs. In contrast, the novel algorithm employs a flexible policy parameterization, suitable for solving general discrete-action MDPs. The algorithm looks for the best closed-loop policy that can be represented using a given number of basis functions, where a discrete action is assigned to each basis function. The locations and shapes of the basis functions are optimized, together with the action assignments. This allows a large class of policies to be represented. The optimization is carried out with the cross-entropy method and evaluates the policies by their empirical return from a representative set of initial states. We report simulation experiments in which the algorithm reliably obtains good policies with only a small number of basis functions, albeit at sizable computational costs.
Abstract: In the near future, intelligent agents on mobile devices will push to as well as request location-dependent information from users at convenient and
inconvenient times. In this paper, we consider the negative effects of mobile agent interruption and present strategies to reduce these effects drawn from
social psychology and task-interruption literature. We propose the implementation of social behaviours to minimize the negative effects of (task) interruptions caused by mobile agents and report the results of two studies that evaluate two social behaviours agents can adopt. The results from these studies
indicate that a mobile agent adopting social system behaviour can lead to a less disruptive user experience.
Abstract: In this delivrable, we present a new protocol to address multilateral multi-issue negotiation in
a cooperative context. We consider complex dependencies between multiple issues by
modelling the preferences of the agents with a multi-criteria decision aid tool, also enabling us
to extract relevant information on a proposal assessment. This information is used in the
protocol to help in accelerating the search for a consensus between the cooperative agents. In
addition, the negotiation procedure is defined in a crisis management context where the
common objective of our agents is also considered in the preferences of a mediator agent.
In fact, in the crisis management problems, the coordination of emergency services and the
evacuation of the injured people are a key issue in the response to a large scale crisis since
lives are at stake. One can observe that the evacuation is based on three important elements:
the examination and classification of the victims, the search for an allocation in the hospitals in
the surrounding area and the transport. In this chapter, we propose to assist the emergency
call centre in the choice of a hospital for each injured man/woman according to his/her
pathology, hospitals constraints and preferences, available transportation and so on. The
negotiation being a process by which a joint decision is made by two or more parties, we
propose a negotiation based approach where agents are led to cooperate in order to achieve a
global goal while trying to satisfy as best as possible individual preferences. This approach
deals with more than two parties, each having its own decision criteria to evaluate an offer
with multiple and dependent issues. Moreover, the preferences of our agents are modelled
using a multi-criteria methodology and tools enabling us to take into account information
about the improvements that can be made to a proposal, in order to help in accelerating the
search for a consensus between the agents. Therefore, we propose a negotiation protocol
consisting of solving our decision problem using a MAS with a multi-criteria decision aiding
modelling at the agent level and a cooperation-based multilateral multi-issue negotiation
protocol. This protocol is studied under a non-cooperative approach and it is shown that it has
subgame perfect equilibria, provided that agents behave rationally. Moreover, these equilibria
converge to the usual maximum solution.
Abstract: Gas distribution models can provide comprehensive information about a large
number of gas concentration measurements, highlighting, for example, areas of unusual
gas accumulation. They can also help to locate gas sources and to plan where
future measurements should be carried out. Current physical modeling methods,
however, are computationally expensive and not applicable for real world scenarios
with real-time and high resolution demands. This chapter reviews kernel methods
that statistically model gas distribution. Gas measurements are treated as random
variables, and the gas distribution is predicted at unseen locations either using a
kernel density estimation or a kernel regression approach. The resulting statistical apmodels
do not make strong assumptions about the functional form of the gas distribution,
such as the number or locations of gas sources, for example. The major
focus of this chapter is on two-dimensional models that provide estimates for the
means and predictive variances of the distribution. Furthermore, three extensions
to the presented kernel density estimation algorithm are described, which allow to
include wind information, to extend the model to three dimensions, and to reflect
time-dependent changes of the random process that generates the gas distribution
measurements. All methods are discussed based on experimental validation using
real sensor data.
Abstract: This report is the second of four documents, which describe the distributed tasking
architecture that has been developed by Thales Research and Technology (UK) Ltd.
This architecture has been developed to test generic tasking and re-tasking policies as
part of the Tasking and Re-tasking sub-project for the Interactive Collaborative
Information Systems (ICIS) programme. This second document focuses on how objects and interfaces have been implemented
to enable centralised tasking algorithms processes to be utilised in the tasking
architecture. Centralised tasking is a traditional, top down approach to tasking whereby
a centralised actor or agent has access to all information about tasks and resources and
is responsible for making all task allocations.
Abstract: This paper introduces the Windmill method for
constructing situation sensitive communication support systems for organizations consisting of a network of autonomous professionals involved in standard duties encountering occasional incidents of a time-critical nature for which they have to call for help. The Windmill method is based on statistical data filtering techniques for ranking available resources to handle incident according to their availability, location, skills and experience. It is especially useful for domains in which the human workforce changes over time and incidents are relatively sparse with respect to location
and frequency of occurrence.