Search

In order to adapt information for a nomadic user equipped with a Mobile Device (MD), an Information System (IS) must take into consideration data that deals with the context of use and user preferences. Data about context of use provides in particular a description of the conditions (temporal, spatial, hardware, etc.) under which users accesses the IS. Data about userpreferences aims at expressing what the user would like to obtain from the system considering different aspects (functionalities, content, display, etc.). In this paper, we propose a Contextual User Profile (CUP) which is made up only of the user preferences which can be satisfied considering the current context of use. We describe the process for generation of the CUP. An example illustrating our proposition is given. We also give the main elements for the design and implementation of a tool supporting our approach. [ABSTRACT FROM AUTHOR]

Multimodal interaction represents the future of human-computer interaction. It aims at enabling users to communicate more freely and naturally with automated systems. Current approaches to multimodal dialogue systems are based on two different strategies to perform the modality fusion. The former implements the multimodal fusion at dialogue management level, whereas the latter at grammar level. In this paper we propose a new strategy based on a hybrid multimodal grammar that puts formal grammars and logical calculus together in order to overcome the drawbacks of grammar-based and dialogue-based methods. Moreover, an application of the proposed approach in the context of a multimodal phone book is given and the experiments that we performed to evaluate the approach are described. [ABSTRACT FROM AUTHOR]

The increasing proliferation of mobile devices has raised the expectations for user-customized and environment-aware services. However, mobile context-aware systems inherently feature characteristics of distribution and heterogeneity which pose great challenges to their developers. This paper focuses on context distribution in mobile and ubiquitous computing environments. We propose a peer-to-peer based context distribution approach and evaluate it against the derived requirements. [ABSTRACT FROM AUTHOR]

As part of the mobile pervasive game, Professor Tanda's 'Guess A Where' [1] there was a need to allocate pre-authored content for the game on a daily basis to provide an enjoyable and engaging experience. To aid this allocation of content we collected and visualized context information about each player during the course of the game. The aim of these visualizations was to provide a method through which an author/orchestrator could retrospectively view a player's current total and daily context data gathered by the game. Observations made about this data could then be used to, not only allocate appropriate content but, to tailor the content to a specific player. This paper presents the data that was gathered and the visualizations created to achieve this process. [ABSTRACT FROM AUTHOR]

As workflow technology evolves into the grid domain, workflow process becomes more and more complex, raising a great challenge both to workflow modeling and workflow execution. In response to the challenge, this paper puts forward a goal-driven workflow framework. The framework first proposes process pattern as an effective way for procedural knowledge representation and then deploys a pattern-based planning algorithm to (semi-) automatically generate workflow on the fly according to the goal specified by users and the running context. Such a goal-driven workflow management paradigm could not only enhance the flexibility and adaptability of workflow system but also ease the heavy burden of workflow definition. [ABSTRACT FROM AUTHOR]

Scientists are increasingly utilizing Grids to manage large data sets and execute scientific experiments on distributed resources. Scientific workflows are used as means for modeling and enacting scientific experiments. Windows Workflow Foundation (WF) is a major component of Microsoft's .NET technology which offers lightweight support for long-running workflows. It provides a comfortable graphical and programmatic environment for the development of extended BPEL-style workflows. WF's visual features ease the syntactic composition of Web services into scientific workflows but do nothing to assure that information passed between services has consistent semantic types or representations or that deviant flows, errors and compensations are handled meaningfully. In this paper we introduce SAWSDL-compliant annotations for WF and use them with a semantic reasoner to guarantee semantic type correctness in scientific workflows. Examples from bioinformatics are presented. [ABSTRACT FROM AUTHOR]

This paper proposes a method of computing semantic similarity which improves accuracy compared to the exisitng approaches. Most of the exisitng approaches uses WordNet as the ontology to calcualte and evaluate the similariy. A method using lightweight ontologies is proposed. The proposed method which considers offset value depends on ontology's hierarchy layer and keyword's importance increases the accuracy of the correlation between computed similarities and human judgements.The method was used in a TV navigation agent system. This system introduces similar TV programs in which the user is interested. Several lightweight ontologies for TV programs to compute semantic similarity between TV programs was also developed. An experiment to evaluate the accuacy was also conducted. [ABSTRACT FROM AUTHOR]

The workload supported by Virtual Organizations (VO) is limited by the quantity of available resources. VOs with scarce resources or peer-to-peer based VOs — due to the dynamicity of available resources — may need extra resources to carry out a given task. Conversely, many Internet-connected computers have surplus bandwidth, storage and computational resources. We face those tradeoffs by enabling VOs to collect and aggregate surplus resources and provide them with availability guarantees to other VOs. This paper presents DyMRA, a decentralized resource allocation system based on markets that allows inter-VO resource allocation. DyMRA is specially designed for dynamic and peer-to-peer environments, where the autonomy of participants to disconnect resources at any time and its decentralized nature requires the capacity to dynamically reallocate resources and services that manage the overall system. DyMRA is built on top of LaCOLLA, a peer-to-peer middleware that allows a group of users to share resources in a collaborative manner. We present the design, architecture and validation of our proposal. [ABSTRACT FROM AUTHOR]

In implicit human computer interaction, computers are required to understand users' actions and intentions so as to provide proactive services. Visual processing has to detect and understand human actions and then transform them as the implicit input. In this paper an adaptive vision system is presented to solve visual processing tasks in dynamic meeting context. Visual modules and dynamic context analysis tasks are organized in a bidirectional scheme. Firstly human objects are detected and tracked to generate global features. Secondly current meeting scenario is inferred based on these global features, and in some specific scenarios face and hand blob level visual processing tasks are fulfilled to extract visual information for the analysis of individual and interactive events, which can further be adopted as implicit input to the computer system. The experiments in our smart meeting room demonstrate the effectiveness of the proposed framework. [ABSTRACT FROM AUTHOR]

In this paper, we propose a mobile user interface named personal companion which enables selection and interaction of u-services based on context of user. Personal companion selects u-services from a list of discovered services, supports camera-based selection with embedded marker and personalizes UI of the selected service in ubiquitous computing environment. In order to verify its usefulness, we implemented personal companion on PDA and UMPC platform and deployed into smart home testbed for selecting and interacting with u-services. The proposed personal companion is expected to play a vital role in ubiquitous computing environment by bridging users and u-services. [ABSTRACT FROM AUTHOR]

AUK is a 3x3 multi-tier onscreen keyboard. It supports various entry modes, including 1 to 10-key and joystick modes, allowing text entry with a remarkable range of devices. This paper presents the menu structure of AUK, the alternative entry modes, and several layouts for novice, moderate and expert users. The potential of AUK, as a text entry solution both for disabled and able-bodied users, is discussed. Overall, the work presented here is considered as a contribution to Universal Access and towards ambient text entry. [ABSTRACT FROM AUTHOR]

We like large displays. Also, we love to equip with multiple displays for exercising multiple tasks in parallel. It is not unusual to have multiple large displays in our offices. Therefore, we can see many widgets on multiple large displays and would like to select and manipulate them in more convenient and faster ways. Because the widgets are physically spread in multiple large displays, it is not easy for users to reach them easily. It follows that new interaction techniques must be provided.[1] New interaction techniques for accessing distant widgets on multiple large displays using a tabletop interface called ‘u-Table' [2] are proposed in this paper. Hand gestures are mainly used on tabletop interfaces because of their intuitive, non-invasive and easy operations. We incorporate advantages of existing techniques such as intuitiveness of tabletop interfaces, fastness and simultaneity of existing interaction techniques such as Drag-and-pick [10] and Vacuum [11]. The proposed interaction techniques include fetching, sending, and manipulating distant widgets on multiple large displays. We expect our techniques can be applied various interfaces using hand gestures and heterogeneous displays. [ABSTRACT FROM AUTHOR]

Due to the shared nature of current network structures, guaranteeing the quality of service (QoS) of Internet applications from an end-to-end is sometimes difficult and then it has been requested to develop smart devices which have multi-modal functionality for ubiquitous network and computing environment. In this paper, we design smart SoftPhone device for guaranteeing QoS which can discover and measure various network parameters during realtime phone-call service through IP network. The smart SoftPhone for discovering and measuring of QoS-factors in realtime consists of four main blocks that is in order to control and measure various parameters independently based on UDP/SIP/RTP protocol during the end-to-end voice service. Also, we provide critical message report procedures and management schemes to guarantee QoS based on using smart SoftPhone device. For the reporting quality parameters optimally during establishing call sessions of VoIP service, we design critical management module blocks for call session and for quality reporting. To sum up, for the performance evaluation of the smart SoftPhone with scientific exactitude of quality factors, we examine the proposed technique based on the realtime phone-call service through heterogeneous network. The experimental results confirm that the developed smart SoftPhone is very useful to quality-measuring for the quality guaranteed realtime VoIP service and then it could also be applied to improve speech quality as a packet compensation device. [ABSTRACT FROM AUTHOR]

In this paper we present current and future approaches to merge intelligent interfaces with immersive Virtual Environments (VEs). The aim of this paper is to substantiate the introductory presentation in the session "Facing Virtual Environments with innovative interaction techniques" at HCI 2007. Although VEs and multimodal interfaces tried to make Human-Computer- Interaction as natural as possible, they have shown serious usability problems. We describe concepts to aid users in supporting their personal cognitive and perceptual capabilities, where the Virtual Environment will adapt dynamically and in real-time to the users' physiological constitution, previous behaviour and desires. With our concept, human performance can be significantly enhanced by adapting interfaces and environments to the users' mental condition and their information management capacity. Health and usability problems caused by stress, workload and fatigue will be avoided. We intend to encourage discussions on this topic among the experts, which are gathered this session. [ABSTRACT FROM AUTHOR]

This paper presents the study of evaluating VR display types on Brain Computer Interface (BCI) performance. In this study, a configurable virtual reality BCI system was used for users to control the virtual environment to execute the ubiquitous computing home facilities. The study evaluated various VR display types: 2D arrow cue, 3D virtual reality, 3D fully immersive CAVE system, and 3D CAVE cue. The task involved users to imagine left or right arm movements for rotating the direction in the virtual environment and move forward by using a direction locking device. The result shows that there was no significant improvement on BCI classification rate even by enhancing the immersion of VR displays. Instead, the level of simulator sickness was increased. This result indicates a new improved display type is needed for the ubiquitous computing environment control BCI system. [ABSTRACT FROM AUTHOR]

This paper presents the Augmented Ambient project that aims to construct a highly interactive mobility scenario based on augmented reality applications running on heterogeneous multimedia devices. Mobility is made available through ambient networks, which are dynamic computer networks. A case study has been performed about a virtual museum, where users join a service network that includes art pieces visualization, broadcast interview, chat, and remote live auctions. These services are implemented in Desktop, Pocket PC and Symbian OS platforms. Each one has its own limitations related to processing power and content exhibition, which are considered during media exchange. The application development process for each supported platform is detailed in the text that presents also some libraries built to simplify and speed up the development, namely OgreAR, OGRE port for Pocket PC and CIDA, beyond the ambient networks related software infrastructure. [ABSTRACT FROM AUTHOR]

GOOD ROUTE is a European project developing a cooperative system for routing, monitoring, re-routing, enforcement and driver support of dangerous goods vehicles, based upon dynamic, real time data, in order to minimise the Societal Risks related to their movements, whereas still generating the most cost efficient solution for all actors involved in their logistic chain. In this paper the theoretical background for the Human-Machine Interface of the GOOD ROUTE system is discussed, different actors are characterised and their user needs are described. Basic functionalities and elements as well as the preliminary guidelines that endorse the GOOD ROUTE system approach are presented. [ABSTRACT FROM AUTHOR]

The paper describes: elements of a continuous improvement system in an enterprise, teamwork as an approach towards solving problems at workstations (especially problems concerning ergonomic issues) and methods and techniques used in ergonomic standards improvement at the stages of problem identification as well as search and implementation of the solutions. Requirements and conditions for efficient implementation are substantiated for improvements such as: training system, motivational system, system of applying and evaluation of applications, financial support of the implementation process and 5S program as a starting point for ergonomic improvements. Theoretical considerations will be illustrated with examples of improvements implemented in Polish enterprises. [ABSTRACT FROM AUTHOR]

In this paper we describe results from our work on adapting speech support in the Opera web browser to disabled users, through using available gross categories of equipment feature (screen presentation and program control) to categorize user and usage characteristics in user profiles. Allocation of users to equipment is based on characteristics of user and equipment, rather than on diagnostic categories. We have combined a number of approaches to investigate how users with different kinds of disabilities may benefit from speech support in the Opera web browser, and how the speech support may be adapted to enhance their utility of this support. After an introduction, we present the method used, the user profiles, and how different types of voice support may be adapted to different (combinations of) profiles. The latter includes both general requirements and suggestions for presentation formats and commands (voice or keyboard) for the profiles. The main conclusions from the work are that the voice support in the version of the Opera web browser that was used in the study is most suitable for people who have reading and writing disorders and that further development of voice support should focus on better adaptation for persons with motor disabilities. Most blind and visually impaired people in Norway already have access to specialized support, and do not need the voice support in Opera. [ABSTRACT FROM AUTHOR]

Context-awareness becomes the key technology in the human computer interaction of ubiquitous computing. The paper discusses the characteristic, significance as well as function of the context, and the properties of the human computer interaction in the ubiquitous environments where the physical space fuses with the information space. These characteristics bring new requirements, that is, mobility, tractability, predictably and personality. To satisfy the demands, we present a method to realize context-awareness and the wireless interaction by using the pervasive RFID tags to track the context and using Bluetooth as the contact-less communication measure. We also construct a prototype system composed of RFID tags, BTEnableReaders and Bluetooth-enable mobile terminals. One case of application scenario is given and the experimental results show that the performance and robustness of the device are suitable for ubiquitous applications and the interaction is experienced more positively by users than the conventional method. The devices we design also can be extended to other application areas such as wearable computing, health care, disable help, and road navigation. [ABSTRACT FROM AUTHOR]

An Ambient Intelligence Research Facility is being set up at ICS-FORTH, with the goal of providing an experimentation platform for Ambient Intelligence (AmI) technologies and for studying their potential impact on users as individuals and as society. This paper discusses the opportunities that such a facility will offer towards the investigation of AmI from a Universal Access perspective, focusing in particular on issues related to Design for All. [ABSTRACT FROM AUTHOR]

Recent advances in ubiquitous computing have evoked the prospect of real-time monitoring of people's health in context-aware homes. Home is the most private place for people and health information is of highly intimate nature. Therefore, users-at-home must have means to benefit from home healthcare and preserve privacy as well. However, most smart home healthcare systems currently lack support for privacy management for home inhabitants. In this paper, we analyze the privacy needs of smart home inhabitants utilizing a healthcare system and present a conceptual framework to manage disclosure of their personal health information. The proposed framework supports sharing the most meaningful detail of personal health information at different time granularities with different recipients in different contexts. To relieve the burden of configuration, default disclosure settings are provided, and to ensure end-user's control over disclosure, the option to override default settings is included. [ABSTRACT FROM AUTHOR]

In this paper we present a procedure to learn a topological model of Situated Public Displays from data of people traveling between these displays. This model encompasses the distance between different displays in seconds for different ways and/or different travel modes. It also shows how many people travel between displays in each direction. Thus, the model can be used to predict where and when people will appear next after showing up in front of one display. This can be used for example to create continuous ‘shows' spanning multiple displays while people pass them. To create the model, we use Bluetooth connection data of mobile phones people carry, and employ the EM algorithm to estimate mean travel times for different paths people take. [ABSTRACT FROM AUTHOR]

In this paper, a Conflict Control Manager (CCM) for a ubiquitous services system is presented to prevent the mode confusion of humans. CCM consists of a lock-based conflict detection module and a D-PRI (dynamic priority)-based conflict resolution. By means of CCM, the mode confusion can drastically be reduced, and, as a result, CCM can assist in designing and implementing a human-centered ubiquitous environment. Through a case study, it is observed that CCM can successfully detect and resolve the runtime conflicts caused by multiple devices interconnected in a ubiquitous environment. It can also be used to detect the potential conflict risk during the service registering phase so that computerized devices are deployed to improve the human interactions with them. [ABSTRACT FROM AUTHOR]

A major challenge of Ambient Intelligence lies in building middleware that can ease service implementation through allowing the application developer to emphasize only the service logic. In this paper we describe the architecture of an Ambient Intelligence system established in the scope of the European research project CHIL (Computers in the Human Interaction Loop). CHIL aims at developing and realizing computer services that are delivered to humans in an implicit and unobtrusive way. The framework presented here supports the implementation of human-centric context-aware applications. This includes the presentation of the sensors used in CHIL spaces, the mechanisms employed for controlling sensors and actuating devices, as well as the perceptual components and the middleware approach for combining them in the scope of applications. Special focus lies on the design and implementation of an agent based framework that supports "pluggable" service logic in the sense that the service developer can concentrate on coding the service logic independently of the underlying middleware. Following the description of the framework, we elaborate on how it has been used to support two prototype context-aware human centric and non-obtrusive services. [ABSTRACT FROM AUTHOR]

Ambient Intelligence (AmI) is considered a likely future embodiment of the information society, according to development scenarios proposed worldwide. With reference to the scenarios developed in Europe by the Information Society Technology Advisory Group (ISTAG), this position paper maintains that, up to now, the attention has been more on the smart objects that are supposed to populate the environment and their interfaces than on the "intelligence" of the entire system. The latter is of paramount importance if users are to be served according to the specifications of the AmI environments. Correspondingly, the current notion of Design for All needs to be revised in order to take into account the additional complexity of the emerging information society. Examples of the main points to be considered are offered in order to elicit discussion. [ABSTRACT FROM AUTHOR]

Ambient Intelligence (AmI) scenarios place strong emphasis on the fact that interaction takes place through natural interfaces, in such a way that people can perceive the presence of smart objects only when needed. As a possible solution to achieving relaxed and enjoyable interaction with the intelligent environments depicted by AmI, the ambient could be equipped with suitably designed multimodal interfaces bringing up the opportunity to communicate using multiple natural interaction modes. This paper discusses challenges to be faced when trying to design multimodal interfaces that allow for natural interaction with systems, with special attention to speech-based interfaces. It describes an application that was built to serve as a test bed and to conduct evaluation sessions in order to ascertain the impact of multimodal natural interfaces on users and to assess their usability and accessibility. [ABSTRACT FROM AUTHOR]

Digital libraries offer substantial volumes of declarative knowledge to the information society. This paper explores the extent to which current and future digital libraries, also known as ubiquitous knowledge environments, can be made sufficiently usable, accessible and smart to support an inclusive information society and the aspiration of universal access. Using a range of converging methods to evaluate a random sample of such digital library websites, it is concluded that, whilst they act as substantial and functional repositories for knowledge, there is potential to improve, particularly in accessibility and smartness. The current methods are validated through the substantial statistical significance levels and by the meaningful patterns found in the resulting data. A new measure of system smartness is introduced and found to provide a useful metric for present purposes, though it is clear that further work will be needed. [ABSTRACT FROM AUTHOR]

This paper presents a formative multi-method evaluation on future gaming systems. Following a scenario-driven approach, quantitative and qualitative methods are employed to elicit feedback from different target user populations. Based on the results of the different evaluation parts, a set of design requirements for future home entertainment systems is derived. These requirements are then used to guide the development process of a ubiquitous computing gaming platform. To demonstrate the usefulness of the gaming platform, a sample application is discussed, which is described in the last section of this paper. [ABSTRACT FROM AUTHOR]

The FAST AIDE (Function Annotated Storyboards Targeting Applicability, Importance, Design, Elaborations) method was developed to capture qualitative and quantitative feedback from highly specialized, expert end-users during the storyboarding stage of new software applications. Unlike traditional approaches, FAST AIDE does not rely on the generation of walk-through scripts or scenarios, but is focused on software features and functionalities. Our rationale is based on the cognitive concept of spreading activation. Spreading activation is hypothesized to occur within knowledge structures similar to organized networks of words or concepts (i.e., nodes). FAST AIDE taps into experiential background of specialized users by utilizing feature dimensions and functionality characteristics to trigger relevant memory. In addition to presenting an approach to knowledge solicitation, FAST AIDE employs a combination data collection questionnaire tool in order to facilitate data evaluation. The paper provides a background and a guide to the implementation of the FAST AIDE method. [ABSTRACT FROM AUTHOR]

Many people suffer from conditions that lead to deterioration of motor control making access to the computer using traditional input devices difficult. In particular, they may loose control of hand movement to the extent that the standard mouse cannot be used as a pointing device. Most current alternatives use markers or specialized hardware, for example, wearable devices, to track and translate a user's movement to pointer movement. These approaches may be perceived as intrusive. Camera-based assistive systems that use visual tracking of features on the user's body often require cumbersome manual adjustment. This paper introduces an enhanced computer vision based strategy where features, for example on a user's face, viewed through an inexpensive USB camera, are tracked and translated to pointer movement. The main contributions of this paper are (1) enhancing a video based interface with a mechanism for mapping feature movement to pointer movement that allows users to navigate to all areas of the screen even with very limited physical movement and (2) providing a customizable, hierarchical navigation framework for human computer interaction (HCI). This framework provides effective use of the vision-based interface system for accessing multiple applications in an autonomous setting. Experiments with several users show the effectiveness of the mapping strategy and its usage within the application framework as a practical tool for desktop users with disabilities. [ABSTRACT FROM AUTHOR]

Hard restrictions in computing power and energy consumption favour symmetric key methods to encrypt the communication in wireless body area networks which in term impose questions on effective and user-friendly unobtrusive ways for key distribution. In this paper, we present a novel approach to establish a secure connection between two devices by shaking them together. Instead of distributing or exchanging a key, the devices independently generate a key from the measured acceleration data by appropriate signal processing methods. Exhaustive practical experiments based on acceleration data gathered from real hardware prototypes have shown that in about 80% of the cases, a common key can be successfully generated. The average entropy of these generated keys exceed 13bits. [ABSTRACT FROM AUTHOR]

When a quadrupedal robot moves, the body and head pitch, yaw and roll, because of its stepping. This natural effect of body and head motion adversely effects the use of visual sensors embedded in the robot's head. Any object in the visual frame of the robot will, from the perspective of the robot, be subject to considerable unmodeled motion or slip. This problem does not affect mammals, which have vestibulo-collic and vestibulo-ocular reflexes that stabilize their gaze in space and maintain objects of interest approximately fixed on the retina. Our work is aimed towards constructing an artificial vestibular system for quadrupedal robots to maintain accurate gaze. This paper describes the first part of this work, wherein we have mounted an artificial vestibular system in a Sony aibo robot. [ABSTRACT FROM AUTHOR]

The increasing interest towards rescue robotics and the complexity of typical rescue environments make it necessary to use high fidelity 3D simulators during the application development phase. USARSim is an open source high fidelity simulator for rescue environments, based on a commercial game engine. In this paper, we describe the development of an autonomous rescue robot within the USARSim simulation environment. We describe our rescue robotic system and present the extensions we made to USARSim in order to have a satisfying simulation of our robot. Moreover, as a case study, we present an algorithm to avoid obstacles invisible to our laser scanner based mapping process. [ABSTRACT FROM AUTHOR]

We present refinements to our previous work on team communication and multi-robot world modeling in the RoboCup legged league. These refinements put high priority on the communication of task-relevant data. We also build upon past results within the simulation and the small-size leagues and contribute a distributed, play-based role assignment algorithm. This algorithm allows the robots to autonomously adapt their strategy based on the current state of the environment, the game, and the behavior of opponents. The improvements discussed in this paper were used by CMDash in the RoboCup 2005 international competition. [ABSTRACT FROM AUTHOR]

In RoboCup small-size league, it is necessary to analyze the opponent robots' behavior in order to make a strategy of the own team. However, it is difficult to prepare image processing methods in advance in order to detect opponent robots' sub-markers used for the orientation detection and identification of the robots, because there is no limitation in the rule in shape, color, arrangement, and the number. This paper proposes a new method to select the most specific sub-marker attached on the top of the robot based on the features such as the size, area, and color values by using the discriminant analysis, and also explains how to extract opponent robots' orientations with some experimental results. [ABSTRACT FROM AUTHOR]

Reinforcement learning is a very general unsupervised learning mechanism. Due to its generality reinforcement learning does not scale very well for tasks that involve inferring subtasks. In particular when the subtasks are dynamically changing and the environment is adversarial. One of the most challenging reinforcement learning tasks so far has been the 3 to 2 keepaway task in the RoboCup simulation league. In this paper we apply reinforcement learning to a even more challenging task: attacking the opponents goal. The main contribution of this paper is the empirical analysis of a portfolio of mechanisms for scaling reinforcement learning towards learning attack policies in simulated robot soccer. [ABSTRACT FROM AUTHOR]

A key feature of human cooperation is that we can coordinate well without communication or negotiation. We achieve this by anticipating the intentions and actions of others, and adapting our own actions to them accordingly. In contrast, most multi-robot systems rely on extensive communication to exchange their intentions. This paper describes the joint approach of our two research groups to enable a heterogeneous team of robots to coordinate implicitly, without negotiation. We apply implicit coordination to a typical coordination task from robotic soccer: regaining ball possession. We discuss the benefits and drawbacks of implicit coordination, and evaluate it by conducting several experiments with our robotic soccer teams. [ABSTRACT FROM AUTHOR]

In some Robocup leagues, specially in the four-legged league, robots make use of coloured landmarks for localisation. Because these landmarks have no correlation with real soccer, it seems a natural approach to remove them. But for this to be a reality, there are some difficulties that need to be solved, mainly an efficient and robust field features detection and an efficient localisation technique to manage such type of information. In this paper we deal with an approach for field features detection based on finding intersections between field lines which runs at frame rate in the AIBO robots. We also present some experimental results of the vision system and a comparison of the traditional coloured landmark localisation and the field features only localisation, both using a fuzzy-Markov localisation technique. [ABSTRACT FROM AUTHOR]

Many approaches for object detection based on color coding were published in the RoboCup domain. They are tuned to the typical RoboCup scenario of constant lighting using a static subdivision of the color space. However, such algorithms will soon be of limited use, when playing under changing and finally natural lighting. This paper presents an algorithm for automatic color training, which is able to robustly adapt to different lighting situations online. Using the ACT algorithm a robot is able to play a RoboCup match while the illumination of the field varies. [ABSTRACT FROM AUTHOR]

This paper presents an efficient way to learn fast omnidirectional quadrupedal walking gaits. We show that the common approaches to control the legs can be further improved by allowing more degrees of freedom in the trajectory generation for the legs. To achieve good omnidirectional movements, we suggest to use different parameters for different walk requests and interpolate between them. The approach has been implemented for the Sony Aibo and used by the GermanTeam in the Four-Legged-League in 2005. A standard learning strategy has been adopted, so that the optimization process of a parameter set can be done within one hour, without human intervention. The resulting walk achieved remarkable speeds, both in pure forward walking and in omnidirectional movements. [ABSTRACT FROM AUTHOR]

Recently, efficient self-localization methods have been developed, among which probabilistic Monte-Carlo localization (MCL) is one of the most popular. However, standard MCL algorithms need at least 100 samples to compute an acceptable position estimation. This paper presents a novel approach to MCL that uses an adaptive number of samples that drops down to a single sample if the pose estimation is sufficiently accurate. Experiments show that the method remains in this efficient single sample tracking mode for more than 90% of the cycles. [ABSTRACT FROM AUTHOR]

This paper focuses on the problem of tracking and predicting the location and velocity of a rolling ball in the RoboCup environment, when the ball is pushed consecutively by a middle-size omnidirectional robot to follow a given path around obstacles. A robust algorithm based on the H ∞  filter is presented to accurately estimate the ball's real-time location and velocity. The performance of this tracking strategy was also evaluated by real-world experiments and comparisons with the Kalman filter. [ABSTRACT FROM AUTHOR]

Autonomous robots can use a variety of sensors, such as sonar, laser range finders, and bump sensors, to sense their environments. Visual information from an onboard camera can provide particularly rich sensor data. However, processing all the pixels in every image, even with simple operations, can be computationally taxing for robots equipped with cameras of reasonable resolution and frame rate. This paper presents a novel method for a legged robot equipped with a camera to use selective visual attention to efficiently recognize objects in its environment. The resulting attention-based approach is fully implemented and validated on an Aibo ERS-7. It effectively processes incoming images 50 times faster than a baseline approach, with no significant difference in the efficacy of its object detection. [ABSTRACT FROM AUTHOR]

Coordination, as a key issue in fully cooperative multiagent systems, raises a number of challenges. A crucial one among them is to efficiently find the optimal joint action in an exponential joint action space. Variable elimination offers a viable solution to this problem. Using their algorithm, each agent can choose an optimal individual action resulting in the optimal behavior for the whole agents. However, the worst-case time complexity of this algorithm grows exponentially with the number of agents. Moreover, variable elimination can only report an answer when the whole algorithm terminates. Therefore, it is unsuitable in real-time systems. In this paper, we propose an anytime algorithm, called the simulated annealing algorithm, as an approximation alternative to variable elimination. We empirically show that our algorithm can compute nearly optimal results with a small fraction of the time that variable elimination takes to find the solution to the same coordination problem. [ABSTRACT FROM AUTHOR]

This paper describes an autonomous learning method used with real robots in order to acquire ball trapping skills in the four-legged robot league. These skills involve stopping and controlling an oncoming ball and are essential to passing a ball to each other. We first prepare some training equipment and then experiment with only one robot. The robot can use our method to acquire these necessary skills on its own, much in the same way that a human practicing against a wall can learn the proper movements and actions of soccer on his/her own. We also experiment with two robots, and our findings suggest that robots communicating between each other can learn more rapidly than those without any communication. [ABSTRACT FROM AUTHOR]

Research efforts in urban search and rescue grew tremendously in recent years. In this paper we illustrate a simulation software that aims to be the meeting point between the communities of researchers involved in robotics and multi-agent systems. The proposed system allows the realistic modeling of robots, sensors and actuators, as well as complex unstructured dynamic environments. Multiple heterogeneous agents can be concurrently spawned inside the environment. We explain how different sensors and actuators have been added to the system and show how a seamless migration of code between real and simulated robots is possible. Quantitative results supporting the validation of simulation accuracy are also presented. [ABSTRACT FROM AUTHOR]

This paper focuses on modelling perception and vague concepts in the context of multiagent Bgi (Beliefs, Goals and Intentions) systems. The starting point is the multimodal formalization of such systems. Then we make a shift from Kripke structures to similarity structures, allowing us to model perception and vagueness in an uniform way, "compatible" with the multimodal approach. As a result we introduce and discuss approximate Bgi systems, which can also be viewed as a way to implement multimodal specifications of Bgi systems in the context of perception. [ABSTRACT FROM AUTHOR]

At present the agent paradigm is often used for computational modeling of human behavior in an organizational setting. However, not many of the existing computational approaches make use of a rich theoretical basis developed in social science. Therefore, often mathematically sound models are invalid in practice. This paper proposes a formal approach for modeling of characteristics and behavior of agents in organizations, diverse aspects of which are represented using an expressive formal framework. The approach is based on the theoretical findings from social science and enables analysis of how different organizational and environmental factors influence the behavior and performance of agents. The approach is illustrated by a simulation case study. [ABSTRACT FROM AUTHOR]

In this paper we focus on a new approach for the definition of context-based compatibility and substitutability of roles in MAS, and provide a formal framework for modeling roles together with their composition. First, we introduce the concept of usability of roles, and based on that we define two flexible roles compatibility relations depending on the context (environment). The proposed compatibility relations take into account the property preservation such as the completion and the proper termination of roles. Then, our formal framework is enhanced with the definition of two flexible behavioral subtyping relations related to the principle of substitutability. Finally, we show the existing link between compatibility and substitutability of roles, namely the preservation of the proposed compatibility relations by substitutability. [ABSTRACT FROM AUTHOR]