Demos

The data on traffic accidents clearly point to the "Black Spots", where the accident rate remains high in months and years. However, road safety research is still far from understanding why this certain place on a road is risky. We tackle the problem by developing \textsc{safeped}, multi agent microscopic 3D simulation of cars' and pedestrians' dynamics at the black spot. SAFEPED: Agent-Based Environment for Estimating Accident Risks at the Road Black Spots Gennady Waizman, Itzhak Benenson

Sustainable Multiagent Application to Conserve Energy Jun-young Kwakhas 3 papers, Pradeep Varakanthamhas 6 papers, Rajiv Maheswaranhas 7 papers, Milind Tambehas 13 papers, Farrokh Jazizadehhas 2 papers, Geoffrey Kavulyahas 2 papers, Laura Kleinhas 2 papers, Burcin Becerik-Gerberhas 2 papers, Timothy Hayeshas 2 papers, Wendy Woodhas 2 papers

Migration is the ability of an agent to transfer from one embodiment, for example a robot, to another such as a mobile phone. For agents that are to act as personal companions migration is desirable as access to different capabilities can provide more constant companionship to a user. This interactive demonstration of screen to phone migration illustrates one application of the open-source architecture developed on the LIREC project to support migration of an affective agent across many types of embodiment. Migrating Artificial Companions Iain Wallace, Michael Kriegel, Ruth Ayletthas 2 papers

Effective Methods for Generating Collision Free Paths for Multiple Robots based on Collision Type Fan Liu, Ajit Narayanan, Quan Bai

The vision of the Smart Grid includes demand-side peak shaving strategies, such as real-time pricing or profile's based tariffs, to encourage consumption such that the peaks on demand are flattened. Up to date, most works along this line focused on optimising via scheduling of home appliances or micro-storage the individual user consumption. Alternatively, in this demonstration we propose to exploit the consumers social side by allowing them to self-organise into coalitions of energy users with complementary needs. To this ends, we present an agent-based Java simulation of a social network of energy consumers (based on the domestic electricity market and usage patterns of homes in the UK) that uses to converge to stable energy coalitions. Decentralised stable coalition formation among energy consumers in the smart grid Filippo Bistaffa, Alessandro Farinellihas 2 papers, Meritxell Vinyals, Alex Rogershas 9 papers

We have developed the virtual world of Omosa in which school students can learn what scientists do by doing it themselves. In Omosa students are able to observe, collect data and interact with a number of intelligent virtual human and animal agents. Learning to be Scientists via a Virtual Field Trip Deborah Richardshas 2 papers, Michael J. Jacobsonhas 2 papers, Meredith Taylorhas 2 papers, Anne Newsteadhas 2 papers, Charlotte Taylorhas 2 papers, John Portehas 2 papers, Iwan Kelaiahhas 2 papers, Nader Hannahas 2 papers

Co-Space refers to interactive virtual environment modelled after the real world in terms of look-and-feel, functionalities and services. We have developed a 3D virtual world named Nanyang Technological University (NTU) Co-Space populated with virtual human characters. In order to create realistic virtual humans, we have designed a brain-inspired agent architecture with the properties of goal-directed autonomy, natural interactivity and human-like personification. The demo will show how the virtual characters may enhance the interactivity and playability of the virtual worlds. Virtual Characters in Agent-Augmented Co-Space Yi-Lin Kang, Budhitama Subagdjahas 2 papers, Ah-Hwee Tanhas 2 papers, Yew-Soon Onghas 2 papers, Chunyan Miaohas 2 papers

We present ARGUS, a coordination system for unmanned aerial vehicles (UAVs) deployed to support situational awareness for disaster management settings. ARGUS is based on the max-sum algorithm, a well known decentralised coordinationalgorithm for multi-agent systems. In this demonstration, we present an interactive simulation environment, where a user acting as a first responder submits imagery collection tasks to a team of UAVs, which then use max-sum to assign themselves to the tasks. We then present a set of real flight tests, in which two Hexacopter UAVs again use ARGUS to coordinate over tasks. Our tests indicate that the system responds positively to the dynamism and the heterogeneity of the real world. ARGUS: A Coordination System to Provide First Responders with Live Aerial Imagery of the Scene of a Disaster Francesco Maria Delle Favehas 2 papers, Alex Rogershas 9 papers, Nick Jenningshas 11 papers

All experiments using intelligent virtual agents, sooner or later, ask for a specific virtual environment that would fit their setup. Seeking such environment is a daunting task accompanied with the need for an appropriate agent adapter that provides infrastructure for mediation of virtual body senses and actions thereby enabling remote high-level agent control. This demo presents Pogamut toolkit, which provides out-of-box programmer tools for creating virtual agents for Unreal Tournament 2004, Unreal Development Kit and Defcon virtual environment. Pogamut’s virtual world abstraction is compatible with many agent oriented languages and architectures including Jadex, GOAL, POSH, Soar or ACT-R, which makes it highly suitable for research on intelligent virtual agents. Pogamut Toolkit Jakub Gemrot, Michal Bídahas 2 papers, Cyril Bromhas 2 papers

Intelligent software agents are increasingly being applied within the smart grid; a future vision of an electricity distribution network where information flows in both ways between consumers and suppliers, and where electricity prices change in real-time in response to the current balance of supply and demand across the grid. In this demonstration, we show a home heating management agent that can learn the thermal characteristics of a home and predict local weather conditions, in order to provide home owners with realtime information about their daily heating costs. Furthermore, we demonstrate how the agent can then optimise heating use to minimise cost and carbon emissions whilst satisfying the home owners preferences for comfort. An Intelligent Agent for Home Heating Management Alex Rogershas 9 papers, Sasan Maleki, Siddhartha Ghosh, Nick Jenningshas 11 papers

With scaling of multi-robot teams deployed in military operations, there is a need to boost autonomy of individual, as well as team behaviors. We developed a feature-rich simulation testbed for experimental evaluation of multi-agent coordination mechanisms applicable in tactical military operations in urban warfare. In particular, we investigated and implemented four approaches including multi-agent mission planning and plan repair, reactive planning for teamwork, patrolling of mobile targets, and tracking of smart targets. Besides the live-system demonstrator, we aim to showcase a scenario engaging a human in a pursuit-evasion game against the algorithms we implemented. Tactical Operations of Multi-Robot Teams in Urban Warfare Peter Novákhas 2 papers, Antonín Komendahas 3 papers, Viliam Lisýhas 2 papers, Branislav Bošanskýhas 3 papers, Michal Čáp, Michal Pĕchoučekhas 6 papers

We present MITRO: Maastricht Intelligent Telepresence RObot, a custom-built robot system specifically designed for augmented telepresence with assisted control. Telepresence robots can be deployed in a wide range of application domains, and augmented presence with assisted control can greatly improve the experience for the user. MITRO: an augmented mobile telepresence robot with assisted control Sjriek Alers, Daan Bloembergenhas 2 papers, Max Bügler, Daniel Henneshas 3 papers, Karl Tuylshas 5 papers

Steering techniques present an important approach to navigation of 3D human-like characters; however, tools for teaching these techniques to students of courses on computer games, computer graphics or software agents are lacking. Here, we present three freely available tools that can be used for this purpose. The first one is a Java library of steering behaviors for Pogamut toolkit for developing control mechanisms of virtual agents. The second one is SteeringTool, an "off-the-shelf" simulation enabling students to investigate how steering rules work in various situations and under a variety of conditions, and the third one is a serious game SteeringGame for motivating students to study this topic. Toolkit for Teaching Steering Behaviors for 3D Human-like Virtual Agents Markéta Popelová, Cyril Bromhas 2 papers, Jakub Tomek, Michal Bídahas 2 papers

As of today, the behavior of avatars in virtual worlds is usually realized by script sequences which provide the illusion of intelligent behavior to the user. In the research project ISReal, our research group developed the first platform for deploying virtual worlds based on Semantic Web technology, which enables agents to reason about and plan with semantically annotated 3D objects. Powerful tool support is required to design agents which exploit the functionality of the ISReal platform. We decided to reuse existing facilities provided by the model-driven \textsc{Bochica} framework for AOSE and extended it with a platform model for agents situated in semantically-enhanced simulated realities. A Development Environment for Engineering Intelligent Avatars for Semantically-enhanced Simulated Realities Stefan Warwas, Matthias Klusch, Klaus Fischer, Philipp Slusallek

DipGame is a testbed for MAS negotiation involving humans. It is very appropriate to run experiments that mix humans and agents. In this demonstration we introduce an application to facilitate the execution of experiments on several machines and with a friendly graphical user interface. Running Experiments on DipGame Testbed Angela Fabregueshas 2 papers, Santiago Biec, Carles Sierrahas 2 papers

Most of MAS methodologies and infrastructures do not consider direct human participation even though humans can be seen as autonomous entities (i.e. human agents). Virtual Worlds (VW) provide all the necessary means for direct human inclusion into software systems. Virtual Institutions (VI) take advantage of this and combine Electronic Institutions (EI) and VWs to engineer MAS applications where humans participate together with software agents. In this demo, we introduce virtual mWater (\emph{v-mWater}), a VI for water rights negotiation. v-mWater: a 3D Virtual Market for Water Rights Pablo Almajano, Tomas Trescak, Marc Esteva, Inmaculada Rodriguez, Maite Lopez-Sanchez

This paper presents a context-aware, multiagent system for care of the elderly. The system combines state-of-the-art sensor technologies to detect falls and other health problems, and calls for help in the case of an emergency or issues a warning in cases not needing urgent attention. When deployed at the home of an elderly person it provides them with 24-hour monitoring. Consequently, the elderly may live alone at home, even at an advanced age. The health problems are detected with six groups of agents processing the sensor data and augmenting the data with higher-level information, such as the posture of the person, his/her activity and the context of the situation's environment. The system has been tested in several live demonstrations, where it achieved an excellent performance in complex situations. The system is based on the set of agents observing the elderly person from various points of view, and combining the location and inertial sensors to provide context awareness. Context-Aware MAS to Support Elderly People Boštjan Kalužahas 2 papers, Mitja Luštrek, Erik Dovgan, Matjaž Gams

Gestational diabetes is a type of diabetes affecting temporarily some otherwise healthy pregnant women. Current medical practices do not allow the doctors to monitor such patients as closely as needed. Pervasive Health is a discipline requiring distributed ICT infrastructures to help bridging the gap between the patients and the doctors. In this demo paper we present a complete information system for patient monitoring, including mobile devices for acquiring data from patients and a Web interface for doctors to check the status of their patients. At the core of this information system a multi-agent system monitors the patient health state and triggers alerts to the doctor to raise attention on the specific conditions of a patient. This allows the doctor to react faster to changes of condition of the woman, benefiting the baby's and the mother's health. Agent Based Monitoring of Gestational Diabetes Mellitus René Schumann, Stefano Bromuri, Johannes Krampf, Michael Schumacher

Traditional approaches to cross-organizational business modeling use low-level abstractions such as data and control flow. These approaches result in rigid models that over-constrain business execution. Further, because such approaches ignore the underlying business relationships that drive process execution, they lack the notion of business level correctness.
Telang and Singh propose a high-level business modeling approach based upon (social) commitments to address these shortcomings. The high-level model captures the business relationships in terms of commitments between the participants. Telang and Singh develop a method for verifying if a low-level interaction model satisfies a high-level business model. They propose a top-down methodology in which a Business analyst first develops a high-level business model. An IT analyst then develops UML 2.0 sequence diagrams, and verifies if they satisfy the high-level model.
Protos is an Eclipse-based tool that implements Telang and Singh's methodology. It enables: (a) the development of a high-level business model using reusable patterns, (b) the development of UML 2.0 sequence diagrams, as a low-level operational representation, and (c) the automated verification of the UML 2.0 sequence diagrams with respect to the high-level business model. Protos: A Cross-Organizational Business Modeling Tool Anup Kalia, Pankaj Telanghas 3 papers, Munindar Singhhas 3 papers

When operating in virtual communities, intelligent agents should maintain a high-level awareness of the physical and social environment around them in order to be more believable and capable. However, due to the inherent differences between virtual worlds and agent systems such as BDI, such a high-level of awareness has not been achieved for IVAs. In this paper we present a system that enables IVAs to maintain a high-level awareness of their environment by identifying complex events taking place in their environment, as well as by being able to monitor for the fulfilment and violation of their expectations. Expectation and Complex Event Handling in BDI-based Intelligent Virtual Agents Surangika Ranathunga, Stephen Cranefield

In this paper a MAS simulation environment is proposed to simulate the migration process in order to observe dynamic behaviours that may emerge at macro level. As a result of this analysis, it has been possible to identify behaviour patterns that can be represented using agent-based models. Moreover, with this approach predictive techniques has been included in order to represent the complex environment of the migration process and its interaction with other processes like Labour and Financial Markets and Security Forces Management. ARGOS: Simulating Migration Processes Oscar Alvarado, N. Ruiz, Adriana Giret, Vicente Julianhas 2 papers, Vicent Bottihas 4 papers, Victor Perez, Rosa Maria Rodriguez

CALU is a multi-robot collision avoidance system based on the velocity obstacle paradigm. In contrast to previous approaches, we alleviate the strong requirement for perfect sensing (i.e. global positioning) using Adaptive Monte-Carlo Localization on a per-agent level. CALU: Collision Avoidance with Localization Uncertainty Daniel Claeshas 2 papers, Daniel Henneshas 3 papers, Karl Tuylshas 5 papers, Wim Meeussenhas 2 papers

We demonstrate the realization of stigmergic coverage for multi-robot systems. Compared to current state-of-the-art algorithms for multi-robot coverage, our Stigmergy-based Coverage algorithm (StiCo) has several key advantages. In particular, it does not need direct robot-robot communication. Moreover, this algorithm does not require any prior information about the environment. Simulation results illustrate robustness, scalability and simplicity of the algorithm. Stigmergic Coverage Algorithm for Multi-Robot Systems Bijan Ranjbar-Sahraei, Gerhard Weisshas 2 papers, Ali Nakisaee

Infraworld is an experimental framework for Computer Aided Engineering (CAE) systems which is designed for distributed design. The framework is based on Multi-agent systems that allow engineers to synchronize their work by keeping track of their changes and facilitating the detection and management of semantic conflicts that arise when different actors are working in parallel. Conflicts are detected according of each engineers semantics which are defined by using OWL ontologies and SWRL rules. When they are detected, the framework allows solving them by negotiating possible alternatives. Then the alternatives are evaluated by expressing preferences and the picked alternative, being the one that maximizes the global welfare, is applied in all the models in the distributed environment. The system is completed with a machine learning module that allows the agents to suggest similar solutions to future conflicts with similar semantic context. Infraworld, a Multi-agent Based Framework to Assist in Civil Infrastructure Collaborative Design Jaume Faus, Francisco Grimaldohas 2 papers

\textsc{AgentPolis} is a fully agent-based platform for modeling multi-modal transportation systems. It comprises a high-performance discrete-event simulation core, a cohesive set of high-level abstractions for building extensible agent-based models and a library of predefined components frequently used in transportation and mobility models. Together with a suite of supporting tools, \textsc{AgentPolis} enables rapid prototyping and execution of data-driven simulations of a wide range of mobility and transportation phenomena. We illustrate the capabilities of the platform on a model of fare inspection in public transportation networks. AgentPolis: Towards a Platform for Fully Agent-based Modeling of Multi-Modal Transportation Michal Jakobhas 2 papers, Zbynĕk Moler, Antonín Komendahas 3 papers, Zhengyu Yinhas 4 papers, Albert Xin Jianghas 2 papers, Matthew Johnson, Michal Pĕchoučekhas 6 papers, Milind Tambehas 13 papers

The purpose of the demonstrator is to present a novel system for gesture-based interaction between humans and a swarm of mobile robots. The human interacts with the swarm by showing hand gestures using an orange glove. Following initial hand glove detection, the robots move to adapt their positions and viewpoints. The purpose is to improve individual sensing performance and maximize the gesture information mutually gathered by the swarm as a whole. Using multi-hop message relaying, robots spread their opinions and the associated confidence about the issued hand gesture throughout the swarm. To let the robots in the swarm integrate and weight the different opinions, we developed a distributed consensus protocol. When a robot has gathered enough evidence, it takes a decision for the hand gesture, and sends it into the swarm. Different decisions compete with each other. The one assessed with the highest confidence eventually wins. When consensus is reached about the hand gesture, the swarm acts accordingly, for example by moving to a location, or splitting into groups.
The working of the system is shown and explained in the video accessible at the following address: {\footnotesize \url{http://www.idsia.ch/~gianni/SwarmRobotics/aamasdemo.zip}} Distributed Consensus for Interaction between Humans and Mobile Robot Swarms Alessandro Giusti, Jawad Nagi, Luca Gambardellahas 2 papers, Gianni Di Carohas 2 papers

Team-It: Location-Based Mobile Games for Multi-Agent Coordination and Negotiation Spencer Frazier, Yu-Han Changhas 3 papers, Alex Newnan, Rajiv Maheswaranhas 7 papers

In an attempt to bridge the gap between the theoretical advances in multiagent decision making algorithms and their application in real world scenario, we present the \emph{Georgia testbed for autonomous control of vehicles (GaTAC)}. GaTAC provides a low-cost, open-source and flexible environment for realistically simulating and evaluating policies generated by multi-agent decision making algorithms in real world problem domains pertaining to control of autonomous uninhabited aerial vehicles (AUAVs). We describe GaTAC in detail and shall demonstrate how GaTAC could be used to simulate an example AUAV problem. We expect GaTAC to facilitate the development and evaluation of scalable decision making algorithms with results that have immediate practical implications. GaTAC: A Scalable and Realistic Testbed for Multiagent Decision Making Ekhlas Sonuhas 2 papers, Prashant Doshihas 3 papers