Fujitsu Laboratories Ltd. and the University of Electro-Communications today announced the development of a high-speed algorithm that uses mathematical game theory as an artificial intelligence technology to aid in the development of security planning. This will work to solve city-scale road network security problems, such as where best to position checkpoints when trying to catch a criminal. For security measures at locations where people gather, it is often not possible to completely seal off all intrusion or escape routes with limited security resources, so it is necessary to effectively deploy security personnel and to minimize anticipated damage. The formulation of security plans has relied on the experience of experts and intuition, but in recent years there has been a focus on game theory, which mathematically describes both offence and defense, as a technology to support expert decision-making. However, it has been difficult to apply game theory to a city-scale security problem of catching criminals at checkpoints in real-world cities because the processing volume expands exponentially with the scale of the road network.

An area coverage control law in cooperation with reinforcement learning techniques is proposed for deploying multiple autonomous agents in a two-dimensional planar area. A scalar field characterizes the risk density in the area to be covered yielding nonuniform placement of agents while providing optimal coverage. This problem has traditionally been addressed in the literature to date using conventional control techniques, such as proportional and proportional--derivative controllers. In most cases, agents' actuator energy required to drive them in optimal configurations in the workspace is not taken into considerations. Here the maximum coverage is achieved with minimum actuator energy required by each agent. Similar to existing coverage control techniques, the proposed algorithm takes into consideration time-varying risk density. Area coverage is modeled using Voronoi tessellations governed by agents. Theoretical results are demonstrated through a set of computer simulations where multiple agents are able to deploy themselves, thus paving the way for efficient distributed Voronoi coverage control problems.

Multi-Agent Systems (MAS) are a common approach to simulating biological systems. Multi-agent modelling provides a natural method for describing individual level behaviours of cells. However, the computation cost of simulating behaviours at an individual level is considerably larger than top down equation based modelling approaches. A recent possibility to improve computational performance is the use of Graphics Processing Units (GPUs) to provide the necessary parallel computing power. In this paper we show that multi-agent models describing biological systems at cellular level are well suited to GPU acceleration. Cellular level systems are characterised by vast numbers of agents that intensively communicate, indirectly through diffusion of chemical substances, or directly, through connection of chemical receptors. We present a study which utilises the FLAME GPU software to target a MAS model of a generic pathogen induced infection to validate the suitability of the GPU for simulation of a broader class of cellular level systems.

The study of the human immune system is an important research area with results that can help improve public health. The human immune system is a natural multiagent system. It is, therefore, liable to be simulated by a corresponding artificial multiagent system. The purpose of this study is to propose a multiagent system for conducting experiments that contribute to highlighting the role of humoral immunity in post-streptococcal glomerulonephritis (PSGN). We identified the requirements for extending the AutoSimmune simulator to simulate key phenomena involved in the emergence of PSGN. Two environments were included: kidney and upper respiratory tract. We also included simulation of neutrophil cells. Furthermore, we simulated the administration of antimicrobials, reporting the consequent reduction of PSGN risk.

Improved collaboration techniques for tasks executed collectively by multiple agents can lead to increased amount of information available to the agents, increased efficiency of resource utilization, reduced interference among the agents, and faster task completion. An example of a multiagent task that benefits from collaboration is Collective Transport with Obstacle Avoidance: the task of multiple agents jointly moving an object while navigating around obstacles. We propose a new approach to sharing and aggregation of information among the transporting agents that entails (1) considering all available information instead of only their own most pressing concerns through establishing objectively valued system needs and (2) being persuadable instead of stubborn, through assessing how these needs compare to the needs established by their peers. Our system extends and improves upon the work in (Ferrante et al. 2013), leading to better informed agents making efficient decisions that cause less inter-agent interference and lead to faster and more reliable completion of the collective task.

This paper presents an ontology-based application for mobile devices which is responsible for supporting groups of people with the management of their shared tasks. The ontology stores the domain knowledge about collaborative tasks, which is used to support task recognition and relocation. Such knowledge is used by a multi-agent system that consists of a group of agents representing each person in the group. The agents use plan recognition techniques to monitor the execution of tasks according to the schedules and negotiate task allocation when needed. Our techniques have been applied in a healthcare scenario which consists of a family group that takes care of an elderly person. This paper presents an ontology-based application for mobile devices which is responsible for supporting groups of people with the management of their shared tasks. % in a healthcare scenario.The ontology stores the domain knowledge about collaborative tasks, which is used to support task recognition and relocation.Such knowledge is used by a multi-agent system that consists of a group of agents representing each person in the group.The agents use plan recognition techniques to monitor the execution of tasks according to the schedules and negotiate task allocation when needed.Our techniques have been applied in a healthcare scenario which consists of a family group that takes care of an elderly person.

In this paper, we examine the effects of probabilistic response on a task allocation problem for a decentralized multi-agent system (MAS) and how such a mechanism may be used to tune the level of redundancy in an MAS. Redundancy refers to a back up pool of agents, beyond the necessary number required to act on a task, that have experience on that task. We present a formal analysis of a response threshold based system in which agents act probabilistically and show that we can estimate the response probability value needed to ensure that a given number of agents will act and that we can estimate the response probability value needed to achieve a given level of redundancy in the system. We perform an empirical study using an agent-based simulation to verify expectations from the formal analysis.

Accurate multiagent social simulation requires a computational model of how people incorporate their observations of real-world events into their beliefs about the state of their world. Current methods for creating such agent-based models typically rely on manual input that can be both burdensome and subjective. In this investigation, we instead pursue automated methods that can translate available data into the desired computational models. For this purpose, we use a corpus of real-world events in combination with longitudinal public opinion polls on a variety of opinion issues. We perform two experiments using automated methods taken from the literature. In our first experiment, we train maximum entropy classifiers to model changes in opinion scores as a function of real-world events. We measure and analyze the accuracy of our learned classifiers by comparing the opinion scores they generate against the opinion scores occurring in a held-out subset of our corpus. In our second experiment, we learn Bayesian networks to capture the same function. We then compare the dependency structures induced by the two methods to identify the event features that have the most significant effect on changes in public opinion.

Planning air missions for a team flying in hostile environments is a complex task, since multiple interrelated goals need to be considered, e.g., performing the mission tasks and avoiding enemy fire. The target assignment and route planning for the team should therefore be performed in a coordinated way. The mission planner suggested in this work combines genetic algorithms and particle swarm optimization in order to solve these two problems in an interconnected manner. Simulations are used for testing and analyzing the approach. It is concluded that the mission planner is able to suggest suitable plans in complex scenarios with three interrelated objectives: low risk exposure, high mission effectiveness and short route length.

For those betting on the 142nd Kentucky Derby on Saturday, there are several ways to approach the strategy. Last year, Jimmy Fallon's puppies took a stab at it--and correctly predicted the winner, American Pharoah. Or, you could rely on the experts from the Bleacher Report. Maybe you want to study up on your own, or see which horses are looking good that day. Go with TechRepublic's Steve Ranger on an inside look at the gold-plated gadget market that's received a big boost from Apple.