In this paper we propose an approach to build a decision support system that can help emergency planners and responders to detect and manage emergency situations. The internal mechanism of the system is independent from the treated application. Therefore, we think the system may be used or adapted easily to different case studies. We focus here on a first step in the decision-support process which concerns the modeling of information issued from the perceived environment and their representation dynamically using a multiagent system. This modeling was applied on the RoboCupRescue Simulation System. An implementation and some results are presented here.

With the most resource intensive tasks in games offloaded to special purpose processors, game designers now have the opportunity to build richer characters using more complex AI techniques than have been used in the past. While additional CPU time makes improved AI feasible, better tools for building agents are needed to make good interactive characters a reality. In this paper we present the BEHAVEngine and BehaviorShop which enable the creation of rich interactive characters.

Time series are found widely in engineering and science.  We study multiagent forecasting in time series, drawing from literature on time series, graphical models, and multiagent systems.  Knowledge representation of our agents is based on dynamic multiply sectioned Bayesian networks (DMSBNs), a class of cooperative multiagent graphical models.  We propose a method through which agents can perform one-step forecast with exact probabilistic inference.  Superior performance of our agents over agents based on dynamic Bayesian networks (DBNs) are demonstrated through experiment.

Partially observable stochastic games (POSGs) provide a rich mathematical framework for planning under uncertainty by a group of agents. However, this modeling advantage comes with a price, namely computation cost. Solving POSGs optimally quickly becomes intractable after a few decision cycles. Our main contribution is to provide bounded approximation techniques which enable us to scale POSG algorithms by several orders of magnitude. We study both the general POSGs and its cooperative counterpart DEC-POMDPs. Experiments on a number of problems confirm the scalability of our approach while still providing useful policies.

This paper addresses the problem of how a group of agents cooperating on a complex plan with interdependent actions can coordinate their scheduling and execution of those actions, particularly in domains where actions may fail or have uncertain durations.  If actions fail (or fail to meet their deadlines), the repercussions for the rest of the team's plan can be dramatic.  This paper presents a pro-active strategy, called Just-in-Time Backfilling (JIT-BF), that agents can use to increase the fault tolerance of their interdependent schedules by identifying actions in danger of failing and inserting redundant (or back-up) actions into their schedules.  The insertion of redundant actions can be done locally (i.e., by the agent whose action is in danger of failing) or through negotiations with the rest of the team. The computations performed by agents following the JIT-BF strategy depend on probabilistic models of action durations and the ``quality'' achieved by successfully executing actions.  The paper presents an experimental evaluation of the JIT-BF strategy within a simulated real-time dynamic environment that demonstrates that teams using the pro-active JIT-BF strategy significantly out-perform teams that rely solely on reactive strategies.

This paper extends the concept of trust modeling within a multi-agent environment.  Trust modeling often focuses on identifying the appropriate trust level for the other agents in the environment and then using these levels to determine how to interact with each agent.  However, this type of modeling does not account for sneaky agents who are willing to cooperate when the stakes are low and take selfish, greedy actions when the rewards rise.  Adding trust to an interactive partially observable Markov decision process (I-POMDP) allows trust levels to be continuously monitored and corrected enabling agents to make better decisions.  The addition of trust modeling increases the decision process calculations, but solves more complex trust problems that are representative of the human world.  The modified I-POMDP reward function and belief models can be used to accurately track the trust levels of agents with hidden agendas.  Testing demonstrates that agents quickly identify the hidden trust levels to mitigate the impact of a deceitful agent.

While team action recognition has a relatively extended literature, less attention has been given to the detailed realtime analysis of the internal structure of the team actions.  This includes recognizing the current state of the action, predicting the next state, recognizing deviations from the standard action model, and handling ambiguous cases. The underlying probabilistic reasoning model has a major impact on the type of data it can extract, its accuracy, and the computational cost of the reasoning process. In this paper we are using Cascading Hidden Markov Models (CHMM) to analyze Bounding Overwatch, an important team action in military tactics. The team action is represented in the CHMM as a plan tree. Starting from real-world recorded data, we identify the subteams through clustering and extract team oriented discrete features. In an experimental study, we investigate whether the better scalability and the more structured information provided by the CHMM comes with an unacceptable cost in accuracy. We find the a properly parametrized CHMM estimating the current goal chain of the Bounding Overwatch plan tree comes very close to a flat HMM estimating only the overall Bounding Overwatch state (a subset of the goal chain) at a respective overall state accuracy of 95% vs 98%, making the CHMM a good candidate for deployed systems.

Using robots as part of any curriculum requires careful management of the significant complexity that physical embodiment introduces. Students need to be made aware of this complexity without being overwhelmed by it, and navigating students through this complexity is the biggest challenge faced by an instructor.  Achieving this requires a framework that allows complexity to be introduced in stages, as students' abilities improve. Such a framework should also be flexible enough to provide a range of application environments that can grow with student  sophistication, and be able to quickly change between applications.  It should be portable and maintainable, and require a minimum of overhead to manage in a classroom. Finally, the framework should provide repeatability and control for evaluating the students' work, as well as for performing research. In this paper, we discuss the advantages of a mixed reality approach to applying robotics to education in order to accomplish these challenges.  We introduce a framework for managing mixed reality in the classroom, and discuss our experiences with using this framework for teaching robotics and AI.

Coalition formation is a fundamental type of interaction that involves the creation of coherent groupings of distinct, autonomous, agents in order to efficiently achieve their individual or collective goals. Forming effective coalitions is a major research challenge in the field of multi-agent systems. Central to this endeavour is the problem of determining which of the many possible coalitions to form in order to achieve some goal. This usually requires calculating a value for every possible coalition, known as the coalition value, which indicates how beneficial that coalition would be if it was formed. Once these values are calculated, the agents usually need to find a combination of coalitions, in which every agent belongs to exactly one coalition, and by which the overall outcome of the system is maximized. However, this coalition structure generation problem is extremely challenging due to the number of possible solutions that need to be examined, which grows exponentially with the number of agents involved. To date, therefore, many algorithms have been proposed to solve this problem using different techniques ranging from dynamic programming, to integer programming, to stochastic search all of which suffer from major limitations relating to execution time, solution quality, and memory requirements. With this in mind, we develop an anytime algorithm to solve the coalition structure generation problem. Specifically, the algorithm uses a novel representation of the search space, which partitions the space of possible solutions into sub-spaces such that it is possible to compute upper and lower bounds on the values of the best coalition structures in them. These bounds are then used to identify the sub-spaces that have no potential of containing the optimal solution so that they can be pruned. The algorithm, then, searches through the remaining sub-spaces very efficiently using a branch-and-bound technique to avoid examining all the solutions within the searched subspace(s). In this setting, we prove that our algorithm enumerates all coalition structures efficiently by avoiding redundant and invalid solutions automatically. Moreover, in order to effectively test our algorithm we develop a new type of input distribution which allows us to generate more reliable benchmarks compared to the input distributions previously used in the field. Given this new distribution, we show that for 27 agents our algorithm is able to find solutions that are optimal in 0.175% of the time required by the fastest available algorithm in the literature. The algorithm is anytime, and if interrupted before it would have normally terminated, it can still provide a solution that is guaranteed to be within a bound from the optimal one. Moreover, the guarantees we provide on the quality of the solution are significantly better than those provided by the previous state of the art algorithms designed for this purpose. For example, for the worst case distribution given 25 agents, our algorithm is able to find a 90% efficient solution in around 10% of time it takes to find the optimal solution.

The topic of risk prevention and emergency response has become a key social and political concern. One approach to address this challenge is to develop Decision Support Systems (DSS) that can help emergency planners and responders to detect emergencies, as well as to suggest possible course of actions to deal with the emergency. Our research work comes in this framework and aims to develop a DSS that must be generic as much as possible and independent from the case study.