Demos

In this paper, we present BDI agent model that social relationships affect agents' evacuation behaviors. The model causes evacuation grouping and breaking in a crowd and the simulation results shows that it generates emergent behaviors in a crowd evacuation as a result of each behavior. Our evacuation simulation provides an analysis tool to assess the safety of occupants in building evacuation. BDI Agent model Based Evacuation Simulation Masaru Okaya, Tomoichi Takahashi

Utilizing principles from parallel and distributed processing combined with inspiration from modular robotics, we developed the modular interactive tiles. As an educational tool, the modular interactive tiles facilitate the learning of multi-agent systems and interactive agent-based games. The modular and physical property of the tiles provides students with hands-on experience in exploring the theoretical aspects underlying multi-agent systems which often appear as challenging to students. By changing the representation of the cognitive challenging aspects of multi-agent systems education to a physical (hands-on) one, the challenge may become much easier and fun to face for the students. An Interactive Tool for Creating Multi-Agent Systems and Interactive Agent-based Games Henrik Hautop Lund, Luigi Pagliarini

This paper presents an attempt on incremental robot learning from demonstration. Based on previously learnt knowledge about a task in simpler situations, a robot learns to fulfill the same task properly in a more complicated situation through analyzing comparative demonstrations and extracting new knowledge, especially the constraints that the task in the new situation imposes on the robot's behaviors. Towards Robot Incremental Learning Constraints from Comparative Demonstration Rong Zhang, Shangfei Wang, Xiaoping Chen, Dong Yin, Shijia Chen, Min Cheng, Yanpeng Lv, Jianmin Ji, Dejian Wang, Peijia Shen

This paper describes a Demo showing the role of the Teleworkbench in the validation process of a multi-agent system, e.g., a traffic management system. In the Demo, we show the capability of the Teleworkbench in seamlessly bridging the simulation and experimentation with real robots. During experiments, important information is logged for analysis purpose. Additionally, a graphical user interface enables geographically distributed users to perform some levels of interactivity, e.g., watch the video or command the robots. Teleworkbench: Validating Robot Programs from Simulation to Prototyping with Minirobots A. Tanoto, F. Werner, U. Rückert, H. Li

We present a MAS decision support tool, as an open and regulated virtual organization, that uses intelligent agents to manage a flexible water-right market. The application goal of this tool is to be used as a simulator to assist in decision-taking processes for policy makers. The simulator focuses on demands and, in particular, on the type of regulatory (in terms of norms selection and agents behaviour), and market mechanisms that foster an efficient use of water while also trying to prevent conflicts among parties. Technically, it contributes with a testbed to explore policy-simulation alternatives under an agreement-technology perspective, thus promoting agreements fulfillment. A MAS Decision Support Tool for Water-Right Markets Adriana Giret, Antonio Garrido, Juan A. Gimeno, Vicente Bottihas 4 papers, Pablo Noriegahas 2 papers

The current implementation provides a demonstration of a number of basic argumentation components that can be applied in the context of multi-agent systems. These components include algorithms for calculating argumentation semantics, as well as for determining the justification status of the arguments and providing explanation in the form of formal discussion games. Furthermore, the current demonstrator also includes the first implementation we know of regarding argument-based judgment aggregation theory. An Implementation of Basic Argumentation Components Mikołaj Podlaszewskihas 2 papers, Martin Caminadahas 2 papers, Gabriella Pigozzihas 2 papers

Recent rise in maritime piracy prompts the search for novel techniques for addressing the problem. We therefore developed AgentC, a prototype system that demonstrates how agent-based traffic management techniques can be used to improve the security of transit through piracy-affected areas. Combining agent-based modeling and simulation of maritime traffic and novel route planning and vessel scheduling techniques, the system shows the promising potential of agent-based methods for increasing maritime security. AgentC: Agent-based System for Securing Maritime Transit Michal Jakobhas 3 papers, Ondřej Vaněkhas 4 papers, Branislav Bošanskýhas 3 papers, Ondřej Hrstka, Michal Pěchoučekhas 5 papers

We show the emergence of Swarm Intelligence in physical robots. We transfer an optimization algorithm which is based on beeforaging behavior to a robotic swarm. In simulation this algorithm has already been shown to be more effective, scalable and adaptive than algorithms inspired by ant foraging. In addition to this advantage, bee-inspired foraging does not require (de-)centralized simulation of environmental parameters (e.g. pheromones). Bee-Inspired Foraging In An Embodied Swarm Sjriek Alers, Daan Bloembergenhas 2 papers, Daniel Henneshas 2 papers, Steven de Jonghas 2 papers, Michael Kaisershas 3 papers, Nyree Lemmens, Karl Tuylshas 4 papers, Gerhard Weiss

The Ultimatum Game is a key exemplar that shows how human play often deviates from “rational” strategies suggested by game-theoretic analysis. One explanation is that humans cannot put aside the assumption of being in a multi-player multi-round environment that they are accustomed to in the real world. We introduce the Social Ultimatum Game (SUG), where players can choose their partner among a society of agents, and engage in repeated interactions of the Ultimatum Game. We develop mathematical models of human play that include “irrational” concepts such as fairness and adaptation to the expectations of the society. We will display a system where people can play SUG against a mixed system of other humans and autonomous agents based on our mathematical models. The Social Ultimatum Game and Adaptive Agents Yu-Han Chang, Rajiv Maheswaran

DipGame is a testbed for negotiation. It permits to test negotiation algorithms, even if enriched with argumentation, trust or reputation techniques. It is very appropriate to run experiments that mix humans and agents. In this demonstration we introduce a tool to visualise data obtained from DipGame experiments. DipTools: Experimental Data Visualization Tool for the DipGame Testbed Angela Fabregues, David López-Paz, Carles Sierrahas 2 papers

talos is a software tool for supporting the development of security applications with mobile patrolling robots. Exploiting talos's functionalities, a user can easily compose a patrolling setting and apply recent algorithms presented in the multi-agent literature to find optimal patrolling strategies. Results can be evaluated and compared with intuitive graphical representations and an interacting game can be played by the user in a simulated patrolling scenario. TALOS: A Tool for Designing Security Applications with Mobile Patrolling Robots Nicola Basilicohas 2 papers, Nicola Gattihas 4 papers, Pietro Testa

This demonstration shows a team of small humanoid robots traverse an environment through a set of obstacles. The robots' brain are implemented using mobile phones for vision, balance, and processing. The robots use particle filters to localize themselves and to map the environment. A frontier-based exploration algorithm is used to direct the robots to overcome obstacles and to explore all regions of the environment. Vision-Based Obstacle Run for Teams of Humanoid Robots Jacky Baltes, Chi Tai Cheng, Jonathan Bagot, John Anderson

We present CASE (complex adaptive systems evolver), a framework devised to conduct the design of agent-based simulation experiments using evolutionary computation techniques. This framework enables one to optimize complex agent-based systems, to exhibit pre-specified behavior of interest, through the use of multi-objective evolutionary algorithms and cloud computing facilities. Evolutionary Design of Agent-based Simulation Experiments James Decraene, Yew Ti Lee, Fanchao Zeng, Mahinthan Chandramohan, Yong Yong Cheng, Malcolm Yoke Hean Low

Narrative time has an important role to play in Interactive Storytelling (IS) systems. In contrast to prevailing IS approaches which use implicit models of time, in our work we have used an explicit model of narrative time. The goal of the demonstration IS system is to show how this explicit temporal representation and reasoning can help overcome certain problems experienced in IS systems such as the coordination of virtual agents and system inflexibility with respect to the staging of virtual agent actions. The fully implemented system features virtual agents and situations inspired by Shakespeare's play The Merchant of Venice. Interactive Storytelling with Temporal Planning Julie Porteoushas 2 papers, Jonathan Teutenberghas 2 papers, Fred Charleshas 2 papers, Marc Cavazzahas 2 papers

We present NeSSi^2 , the Network Security Simulator, a simulation environment that is based on the service-centric agent platform JIAC. It focuses on network security-related scenarios such as attack analysis and evaluation of countermeasures. We introduce the main NeSSi^2 concepts and discuss the motivation for realizing them with agent technology. Then, we present the individual components and examples where NeSSi^2 has been successfully applied. Agent-based Network Security Simulation Dennis Grunewald, Marco Lützenbergerhas 2 papers, Joël Chinnow, Rainer Bye, Karsten Bsufka, Sahin Albayrakhas 2 papers

This paper describes a Multi-robot System, its features and a set of experiments that show its performance under different conditions (e.g., network and sensor unrealiability, number of robots, etc). The system has been fully deployed in a simulated environment; in addition, experiments with a hybrid team of cooperating simulated and real robots will be presented. Experimental Evaluation of Teamwork in Many-Robot Systems Andrea D'Agostini, Daniele Calisi, Alberto Leo, Francesco Fedi, Luca Iocchi, Daniele Nardi