No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Roboskeleton: An architecture for coordinating robot soccer agents
Abstract
SkeletonAgent is an agent framework whose main feature is to integrate different artificial intelligent skills, like planning or learning, to obtain new behaviours in a multi-agent environment. This framework has been previously instantiated in a deliberative domain (electronic tourism), where planning was used to integrate Web information in a tourist plan. RoboSkeleton results from the instantiation of the same framework, SkeletonAgent, in a very different domain, the robot soccer. This paper shows how this architecture is used to obtain collaborative behaviours in a reactive domain. The paper describes how the different modules of the architecture for the robot soccer agents are designed, directly showing the flexibility of our framework.
... More recently, multiple autonomous mobile robots have been proposed for use in rescue missions [11], [12], exploration [13], [14], [15], military applications, and even entertainment with robotic soccer teams [16], [17]. ...
... and (5.11), the EKF is based on two main sets, the time update and the measurement update. These sets are defined by: Time update set: 16) and the measurement update set: ...
... Pour ce faire, le partage d'informations capteurs comme la localisation de l'ensemble des véhicules ou les retours vidéo et sonore vers un opérateur distant assurent une couverture rapide et optimale de la recherche. D'autres types de missions collaboratives ont déjàété envisagées tels que le sauvetage par des systèmes mutli-robots [11], [12], l'exploration coopérative [13], [14], [15], ou les jeux d'équipe [16], [17]. Pour réaliser ces tâches, différentes techniques de contrôle coopératif ont déjàété abordées, par exemple des stratégies centralisées ou décentralisées. ...
This work proposes a control architecture for a group of nonholonomic robotic vehicles. We present a decentralized control strategy that permits each vehicle to autonomously compute an optimal trajectory by using only locally generated information. We propose a method to incorporate reactive terms in the path planning process which adapt the trajectory of each robot, thus avoiding obstacles and maintaining communication links while it reaches the desired positions in the robot formation. We provide the proof of the reachability of the trajectory generation between the current and desired position of each follower. Simulation results validate and highlight the efficiency and relevance of this method. An integration of the wireless network signal strength data with the vehicle sensors information by means of a Kalman filter is proposed to estimate the relative position of each vehicle in a robot formation set. Vehicle sensors consist of wheel speed and steering angle, the WiFi data consist of reception signal strength (RSS) and the angle of the maximal RSS with respect to the robot orientation. A nonholonomic nonlinear model vehicle is considered; due to these nonlinearities an Extended Kalman Filter EKF is used. Simulation and experimental results of the proposed estimation strategy are presented.
... In this paper we want to determine whether human input/output modeling of persons works in principie in the Robosoccer domain. To achieve this, we have used a simpler situation where a single human-controlled agent plays against a defensive opposite team (Camacho, Fernández, & Rodelgo, 2006; Fernandez, Gutiérrez, & Molina, 2000). This team is based on zones, where each of the team members is located. ...
... This latter problem could not be solved, because the Robosoccer server was not designed with interactive play in mind. As our aim is to show that human experience can be transferred to soccer agents, we have chosen a challenging but beatable Robosoccer team (Camacho et al., 2006; Fernandez et al., 2000), which has the advantage that although their players have a team behavior, we can use as many players as desired. In this case, only four of them were used. ...
... In this case, only four of them were used. In any case, it must be remarked that, although the (Camacho et al., 2006; Fernandez et al, 2000) team is not a Robocup champion, it is still a very challenging situation , because: ...
The Robosoccer simulator is a challenging environment for artificial intelligence, where a human has to program a team of agents and introduce it into a soccer virtual environment. Most usually, Robosoccer agents are programmed by hand. In some cases, agents make use of Machine learning (ML) to adapt and predict the behavior of the opposite team, but the bulk of the agent has been preprogrammed.The main aim of this paper is to transform Robosoccer into an interactive game and let a human control a Robosoccer agent. Then ML techniques can be used to model his/her behavior from training instances generated during the play. This model will be used later to control a Robosoccer agent, thus imitating the human behavior. We have focused our research on low-level behavior, like looking for the ball, conducting the ball towards the goal, or scoring in the presence of opponent players. Results have shown that indeed, Robosoccer agents can be controlled by programs that model human play.
... More recently, multiple autonomous mobile robots have been proposed for use in rescue missions [11], [12], exploration [13], [14], [15], military applications, and even entertainment with robotic soccer teams [16], [17]. ...
... and (5.11), the EKF is based on two main sets, the time update and the measurement update. These sets are defined by: Time update set: 16) and the measurement update set: ...
... Pour ce faire, le partage d'informations capteurs comme la localisation de l'ensemble des véhicules ou les retours vidéo et sonore vers un opérateur distant assurent une couverture rapide et optimale de la recherche. D'autres types de missions collaboratives ont déjàété envisagées tels que le sauvetage par des systèmes mutli-robots [11], [12], l'exploration coopérative [13], [14], [15], ou les jeux d'équipe [16], [17]. Pour réaliser ces tâches, différentes techniques de contrôle coopératif ont déjàété abordées, par exemple des stratégies centralisées ou décentralisées. ...
Ces travaux concernent l'elaboration d'une stratégie de commande décentralisée réactive pour une flottille de robots mobiles terrestres. Cette stratégie de commande est basée sur un contrôle décentralisé qui s'appuie sur le principe Leader-Follower utilisant à la fois des informations de positionnement absolu (GPS) et relatif entre véhicules (niveau de réception des liens WiFi) ainsi que des informations d'existence d'obstacles de proximités (capteurs ultra-sons). Cette méthode permet d'intégrer et d'optimiser à chaque instant ces diverses contraintes afin de générer un chemin faisable. Mais également de maintenir la flotille dans une forme géometrique donnée, avec un niveau de réception des transmissions entre les véhicules minimal, tout en évitant d'éventuels obstacles.
... ICT diffusion in small and medium-sized tourism enterprises (SMTEs); e-commerce; business-toconsumer (B2C) e-commerce; travel applications; web page design; spatial data infrastructure; agent technology; reputation-based electronic tourism (RET); skeleton agent; RoboSkeleton; multi-agent environment; logic programming; personalization, information filtering and recommendation; 3D e-tourism environment; CRM for self-service technologies (Berger et al., 2007;Buhalis and Deimezi, 2004;Camacho et al., 2006;Oliver Fodor and Werthner, 2005;Hsiao et al., 2015;Popescu et al., 2006;Scholten et al., 2006;Stockdale, 2007;Susser and Ariga, 2006;Zanker et al., 2006) 2009-2012 ...
Purpose
E-tourism is instilling in the tourism industry with the advancement in the technological infrastructure all over the world and fetching tremendous tourists’ attention. The dynamic changes in the technological aspects unveil varied developments in the tourism industry. This paper attempts to reveal the developments in the field of e-tourism by a systematic review of the literature using bibliometric analysis.
Design/methodology/approach
In total,146 research articles were retrieved from the Web of Science data during the period of 2004 – 2020, for further analysis using VOSviewer and Biblioshiny package of R Studio.
Findings
Useful insights resulted in the form of most cited papers, contribution in e-tourism research by different authors, countries, institutions, journals and so on, co-occurrence analysis and cluster analysis for major trends or themes of e-tourism. This study solicits an elaborated review of e-tourism research and unveils the future directions for the researchers.
Originality/value
This study adds substantial value to the research of e-tourism by analysing the bibliometric data of the last 16 years, that is, from 2004 – 2020, procured from the Scopus by analysing the significant trends developed in the e-tourism research. It also adds value by indicating the emerging areas of e-tourism.
... Planning has been an area of research in artificial intelligence (AI) for over three decades. A variety of tasks including robotics (Diaz et al. 2013), Web-based information gather-ing (Kuter et al. 2005), autonomous agents (Camacho et al. 2006), and mission control (Vachtsevanos et al. 2005) have benefited from planning techniques. Moreover, mission planning is a common problem in AI. ...
Due to recent booming of unmanned air vehicles (UAVs) technologies, these are being used in many fields involving complex tasks. Some of them involve a high risk to the vehicle driver, such as fire monitoring and rescue tasks, which make UAVs excellent for avoiding human risks. Mission planning for UAVs is the process of planning the locations and actions (loading/dropping a load, taking videos/pictures, acquiring information) for the vehicles, typically over a time period. These vehicles are controlled from ground control stations (GCSs) where human operators use rudimentary systems. This paper presents a new multi-objective genetic algorithm for solving complex mission planning problems involving a team of UAVs and a set of GCSs. A hybrid fitness function has been designed using a constraint satisfaction problem to check whether solutions are valid and Pareto-based measures to look for optimal solutions. The algorithm has been tested on several datasets, optimizing different variables of the mission, such as the makespan, the fuel consumption, and distance. Experimental results show that the new algorithm is able to obtain good solutions; however, as the problem becomes more complex, the optimal solutions also become harder to find.
... Wheeled mobile robots have been widely studied and attracted interests of many researches because of their wide applications in industries and theoretical challenges Kolmanovsky and McClamroch [1995]. More recently, wheeled mobile robots have been proposed for using in rescue missions Murphy et al. [2009], explorations Rooker and Birk [2007], tour guide Han et al. [2010], and even entertainment such as robot soccer games Camacho et al. [2006]. Indeed, the mobile robot navigation problem is of great importance, and there are considerable researches effort into solving the robot navigation problems in different applications Salichs and Moreno [2000]. ...
This paper presents the real-time identification of different types of non-holonomic mobile robot systems. Since the robot type is unknown, the robot systems are formulated as a witched singular nonlinear system, and the problem becomes the real-time identification of the switching signal, and then the existence of the input-output functions and the distinguishability of the system are studied. We show in the simulations that the technique is implemented easily and effectively, and it is robust to the noises as well.
... Planning has been an area of research in Artificial Intelligence (AI) for over three decades. A variety of tasks including robotics [10] [11], web-based information gathering [12][13] [14], autonomous agents [15][16] [17] and mission control [18] have benefited from planning techniques. ...
The problem of Mission Planning for a large number of Unmanned Air Vehicles (UAV) can be formulated as a Temporal Constraint Satisfaction Problem (TCSP). It consists on a set of locations that should visit in different time windows, and the actions that the vehicle can perform based on its features such as the payload, speed or fuel capacity. In this paper, a temporal constraint model is implemented and tested by performing Backtracking search in several missions where its complexity has been incrementally modified. The experimental phase consists on two different phases. On the one hand, several mission simulations containing (n) UAVs using different sensors and characteristics located in different waypoints, and (m) requested tasks varying mission priorities have been carried out. On the other hand, the second experimental phase uses a backtracking algorithm to look through the whole solutions space to measure the scalability of the problem. This scalability has been measured as a relation between the number of tasks to be performed in the mission and the number of UAVs needed to perform it.
... In real world, agent often follows some given action decision-making rules, i.e., there is a known or potential mapping relationship between situations and actions. For example, robots with reactive intelligent system architecture121314 have action preference for each situation. Obviously, to beat the opponent with action preference, it is helpful to take the action preference of opponent into account. ...
The proposed self-adaptive predictive pursuing policy consists of an action deci- sion-making procedure and a procedure of adjusting the estimation of evader's action preference. Since correct estimation of opponent's intention would do good to win ad- versarial games, it introduces the conception of action preference to model opponent's decision-making. Because evader often has different action preference in different situa- tion, to model evader's decision-making, pursuer has to divide the situation space into many categories and provide a set of estimation of evader's action preference for each kind of situation. Pursuer adjusts the estimation of evader's action preference in certain situation by observing evader's action. Action decision-making procedure consists of situation sorting, possible future states computation, payoff evaluation and action selec- tion. Action decision-making is based on the decision tree constructed by expected pay- offs. Expected payoffs are integrated from single payoffs. Single payoffs are evaluated by gains of features reflecting adversarial situation. A simulation of middle size soccer robots has been carried out and illustrated that the proposed policy is effective.
The Engineering Applications of Artificial Intelligence (EAAI) is a journal of very high repute in the domain of Engineering and Computer Science. This paper gives a broad view of the publications in EAAI from 1988–2018, which are indexed in Web of Science (WoS) and Scopus. The main purpose of this research is to bring forward the prime impelling factors that bring about the EAAI publications and its citation structure. The publication and citation structure of EAAI is analyzed, which includes the distribution of publication over the years, citations per year and a bird’s eye view of the citation structure. Then the co-citation analysis and over the year’s trend of top keywords is given. The co-authorship networks and a geographic analysis of the sources is also provided. Further, a country-wise temporal and quantitative analysis of the publications is given along with the highly cited documents among the EAAI publications.
The difficulty of coordinating a group of mobile robots is adressed in this thesis by investigating control architectures which aim to break task complexity. In fact, multi-robot navigation may become rapidly inextricable, specifically if it is made in hazardous and dynamical environment requiring precise and secure cooperation. The considered task is the navigation of a group of mobile robots in unknown environments in presence of (static and dynamic) obstacles. To overcome its complexity, it is proposed to divide the overall task into a set of basic behaviors/controllers (obstacle avoidance, attraction to a dynamical target, planning, etc.). Applied control is chosen among these controllers according to sensors information (camera, local sensors, etc.). The specificity of the theoretical approach is to combine the benefits of multi-controller control architectures to those of multi-agent organizational models to provide a high level of coordination between mobile agents-robots systems. The group of mobile robots is then coordinated according to different norms and specifications of the organizational model. Thus, activating a basic behavior in favor of another is done in accordance with the structural constraints of the robots in order to ensure maximum safety and precision of the coordinated movements between robots. Cooperation takes place through a supervisor agent (centralized) to reach the desired destination faster ; unexpected events are individually managed by the mobile agents/robots in a distributed way. To guarantee performance criteria of the control architecture, hybrid systems tolerating the control of continuous systems in presence of discrete events are explored. In fact, this control allows coordinating (by discrete part) the different behaviors (continuous part) of the architecture. The development of ROBOTOPIA simulator allowed us to illustrate each contribution by many results of simulations.
In the field of robot navigation, a number of different approaches have been proposed. One of these is Hybrid Fuzzy A* (HFA), which uses the A* algorithm to determine the long term path from the robot to some target, and fuzzy logic to move the robot to each waypoint along the path. This algorithm has been shown to be fast and effective in simulation, however A* is limited in the variables it can consider and the challenges it can be applied to. We propose replacing A* with Q-learning, which does not suffer from these limitations. We demonstrate the ability of Hybrid Fuzzy Q-Learning (HFQL) to navigate a robot to a given target and then apply the algorithm to a different challenge where the robot needs to balance reaching the target quickly against picking up as many subgoals as possible.
Multi-robot systems provide system redundancy and enhanced capability versus single robot systems. Implementations of these systems are varied, each with specific design approaches geared towards an application domain. Some traditional single robot control architectures have been expanded for multi-robot systems, but these expansions predominantly focus on the addition of communication capabilities. Both design approaches are application specific and limit the generalizability of the system. This work presents a redesign of a common single robot architecture in order to provide a more sophisticated multi-robot system. The single robot architecture chosen for application is the Three Layer Architecture (TLA). The primary strength of TLA is in the ability to perform both reactive and deliberative decision making, enabling the robot to be both sophisticated and perform well in stochastic environments. The redesign of this architecture includes incorporation of the Unified Behavior Framework (UBF) into the controller layer and an addition of a sequencer-like layer (called a Coordinator) to accommodate the multi-robot system. These combine to provide a robust, independent, and taskable individual architecture along with improved cooperation and collaboration capabilities, in turn reducing communication overhead versus many traditional approaches. This multi-robot systems architecture is demonstrated on the RoboCup Soccer Simulator showing its ability to perform well in a dynamic environment where communication constraints are high.
The robot soccer game has been proposed as a benchmark problem for the artificial intelligence and robotic researches. Decision-making system is the most important part of the robot soccer system. As the environment is dynamic and complex, one of the reinforcement learning (RL) method named FNN-RL is employed in learning the decision-making strategy. The FNN-RL system consists of the fuzzy neural network (FNN) and RL. RL is used for structure identification and parameters tuning of FNN. On the other hand, the curse of dimensionality problem of RL can be solved by the function approximation characteristics of FNN. Furthermore, the residual algorithm is used to calculate the gradient of the FNN-RL method in order to guarantee the convergence and rapidity of learning. The complex decision-making task is divided into multiple learning subtasks that include dynamic role assignment, action selection, and action implementation. They constitute a hierarchical learning system. We apply the proposed FNN-RL method to the soccer agents who attempt to learn each subtask at the various layers. The effectiveness of the proposed method is demonstrated by the simulation and the real experiments.
Resumen El principal problema a que nos enfrentamos al diseñar sistemas multi-agente es cómo coordinar los agentes que pertenecen a este sistema para obtener un comportamiento global eficiente. En algunos trabajos, el comportamiento coordinado de los agentes se obtiene gracias a un conocimiento total del dominio en el que se pueden aplicar planificadores tradicionales. Sin embargo, en muchos dominios esta aproximación no es posible por tratarse de dominios demasiado grandes y la comunicación y capacidad de memoria de los agentes muy limitada. En este trabajo se presenta un diseño multi-agente que permite obtener un comportamiento global coordinado basado en los comportamientos reactivos de los agentes que son controlados o dirigidos por la información local que poseen. En el diseño se ha minimizado la comunicación entre los agentes, ya que el proceso de coordinación se basa en reglas locales reactivas. Esta propuesta tiene una primera aplicación en el dominio de la RoboCup (Robot World Cup Iniciative), proyecto ampliamente utilizado por la comunidad investigadora. Palabras Clave: Inteligencia artificial distribuida, sistemas multi-agente, comportamientos cooperativos, comportamientos reactivos, RoboCup.
Adaptation in open, multi-agent information gathering systems isimportant for several reasons. These reasons include the inability toaccurately predict future problem-solving workloads, future changes inexisting information requests, future failures and additions of agents anddata supply resources, and other future task environment characteristicchanges that require system reorganization. We have developed a multi-agentdistributed system infrastructure, RETSINA (REusable Task Structure-based Intelligent Network Agents) that handles adaptation in an open Internetenvironment. Adaptation occurs both at the individual agent level as well asat the overall agent organization level. The RETSINA system has three typesof agents. Interface agents interact with the userreceiving user specifications and delivering results. They acquire, model,and utilize user preferences to guide system coordination in support of theusers tasks. Task agents help users perform tasks byformulating problem solving plans and carrying out these plans throughquerying and exchanging information with other software agents. Information agents provide intelligent access to a heterogeneouscollection of information sources. In this paper, we concentrate on theadaptive architecture of the information agents. We use as the domain ofapplication WARREN, a multi-agent financial portfolio management system thatwe have implemented within the RETSINA framework.
This paper presents a model for the control of autonomous robots that allows cooperation among them. The control structure is based on a general purpose multi-agent architecture using a hybrid approach made up by two levels. One level is composed of reactive skills capable of achieving simple actions by their own. The other one uses an agenda used as an opportunistic planning mechanism to compound, activate and coordinate the basic skills. This agenda handles actions both from the internal goals of the robot or from other robots. This two level approach allows the integration of real-time response of reactive systems needed for robot low-level behavior, with a classical high level planning component that permits a goal oriented behavior. The paper describes the architecture itself, and its use in three different domains, including real robots, as well as the issues arising from its adaptation to the RoboCup simulator domain.
Reinforcement learning has proven to be a set of successful techniques for finding optimal policies on uncertain and/or dynamic
domains, such as the RoboCup. One of the problems on using such techniques appears with large state and action spaces, as
it is the case of input information coming from the Robosoccer simulator. In this paper, we describe a new mechanism for solving
the states generalization problem in reinforcement learning algorithms. This clustering mechanism is based on the vector quantization
technique for signal analog-to-digital conversion and compression, and on the Generalized Lloyd Algorithm for the design of
vector quantizers. Furthermore, we present the VQQL model, that integrates Q-Learning as reinforcement learning technique
and vector quantization as state generalization technique. We show some results on applying this model to learning the interception
task skill for Robosoccer agents.
In the RETSINA multi-agent system, each agent is provided with an internal planning component—HITaP. Each agent, using its internal planner, formulates detailed plans and executes them to achieve local and global goals. Knowledge of the domain is distributed among the agents, therefore each agent has only partial knowledge of the state of the world. Furthermore, the domain changes dynamically, therefore the knowledge available might become obsolete.
To deal with these issues, each agent’s planner allows it to interleave planning and execution of information gathering actions, to overcome its partial knowledge of the domain and acquire information needed to complete and execute its plans. Information necessary for an agent’s local plan can be acquired through cooperation by the local planner firing queries to other agents and monitoring for their results. In addition, the local planner deals with the dynamism of the domain by monitoring it to detect changes that can affect plan construction and execution. Teams of agents, each of which incorporates a local RETSINA planner have been implemented. These agents cooperate to solve problems in different domains that range from portfolio management to command and control decision support systems.
This paper presents a model to define heterogeneous agents that solve problems by sharing the knowledge retrieved from the WEB, and cooperating among them. The control structure of those agents is based on a general purpose Multi-Agent architecture (SKELETONAGENT) based on a deliberative approach. Any agent in the architecture is built by means of several interrelated modules: control module, language and communication module, skills modules, knowledge base, yellow pages, etc. The control module uses an agenda to activate and coordinate the agent skills. This agenda handles actions from both the internal goals of the agent and from other agents in the environment. In the paper, we show a high level agent model, which is later instantiated to build a set of heterogeneous specialized agents. The paper describes how SKELETONAGENT has been used to implement different kinds of agents and a specialized Multi-Agent System (MAS). The implemented MAS, MAPWEB-ETOURISM, is the specific implementation of a general WEB gathering architecture, named MAPWEB, which extends SKELETONAGENT. MAPWEB has been designed to solve problems in WEB domain through the integration of information gathering and planning techniques. The MAPWEB-ETOURISM system has been applied to a specific WEB domain (e-tourism) which uses information gathered directly from several WEB sources (plane, train, and hotel companies) to solve travel problems. This paper shows how the proposed architecture allows to integrate the different agents tasks with AI techniques like planning to build a MAS which is able to gather and integrate information retrieved from the WEB to solve problems. Publicado
Nowadays, multi-agent frameworks allow to implement very complex systems by means of agent technology. However, this complexity makes it more difficult to evaluate software and runtime characteristics of multiagent systems (MAS). Our aim is to define and study some quantitative measures to measure MAS aspects like development time, reusability, scalability, etc. These measures could be used by engineers to guide the selection among several MAS frameworks. Our study has been carried out in several MAS frameworks like JADE, JATLite, SkeletonAgent, and ZEUS, which have been used to build a MAS application for news retrieval. Publicado
This paper presents solutions for one requirement of autonomous characters in animation and games: the ability to navigate around their world in a life-like and improvisational manner. These "steering behaviors" are largely independent of the particulars of the character's means of locomotion. Combinations of steering behaviors can be used to achieve higher level goals (For example: get from here to there while avoiding obstacles, follow this corridor, join that group of characters...) This paper divides motion behavior into three levels. It will focus on the middle level of steering behaviors, briefly describe the lower level of locomotion, and touch lightly on the higher level of goal setting and strategy.
RoboCup Challenge offers a set of challenges for intelligent agent researchers using a friendly competition in a dynamic, real-time, multi-agent domain: synthetic Soccer. While RoboCup in general envisions longer range challenges over the next few decades, RoboCup Challenge presents three specific challenges for the next two years: (i) learning of individual agents and teams; (ii) multi-agent team planning and plan-execution in service of teamwork; and (iii) opponent modeling. RoboCup Challenge provides a novel opportunity for researchers in planning and multi-agent arenas --- it not only supplies them a concrete domain to evalute their techniques, but also challenges them to evolve these techniques to face key constraints fundamental to this domain: real-time and teamwork.
In this paper, we present a multiagent system approach with the purpose of building computer programs. Each agent in the multiagent system will be in charge of evolving a part of the program, which in this case, can be the main body of the program or one of its different subroutines. There are two kinds of agents: the manager agent and the genetic programming (GP) agents. The former is in charge of starting the system and returning the results to the user. The GP agents include skills for evolving computer programs, based on the genetic programming paradigm. There are two sorts of GP agents: some can evolve the main body of the program and the others evolve its subroutines. Both kinds of agents cooperate by telling each other their best results found so far, so that the search for a good computer program is made more efficient. In this paper, this multiagent approach is presented and tested empirically.
The concept of an agent has recently become important in Artificial Intelligence (AI), and its relatively youthful subfield, DistributedAI (DAI). Our aim in this paper is to point the reader at what we perceive to be the most important theoretical and practical issues associated with the design and construction of intelligent agents. For convenience, we divide the area into three themes (though as the reader will see, these divisions are at times somewhat arbitrary). Agent theory is concerned with the question of what an agent is, and the use of mathematical formalisms for representing and reasoning about the properties of agents. Agent architectures can be thought of as software engineering models of agents; researchers in this area are primarily concerned with the problem of constructing software or hardware systems that will satisfy the properties specified by agent theorists. Finally, agent languages are software systems for programming and experimenting with agents; these languages typically embody principles proposed by theorists. The paper is not intended to serve as a tutorial introduction to all the issues mentioned; we hope instead simply to identify the key issues, and point to work that elaborates on them. The paper closes with a detailed bibliography, and some biblographical remarks.
"December 15, 1998." Thesis (Ph. D.)--Carnegie Mellon University, 1998. Includes bibliographical references. Supported in part by the NASA Graduate Student Research Program (GSRP) Supported in part by the Defense Advanced Research Projects Agency (DARPA), and Rome Laboratory, Air Force Materiel Command, USAF. Supported in part by the Department of the Navy, Office of Naval Research.
Agent technology has been considered as an important approach for developing distributed intelligent manufacturing systems. A number of researchers have attempted to apply agent technology to manufacturing enterprise integration, supply chain management, manufacturing planning, scheduling and control, materials handling, and holonic manufacturing systems. This paper gives a brief survey of some related projects in this area, and discusses some key issues in developing agent-based manufacturing systems such as agent technology for enterprise integration and supply chain management, agent encapsulation, system architectures, dynamic system reconfiguration, learning, design and manufacturability assessments, distributed dynamic scheduling, integration of planning and scheduling, concurrent scheduling and execution, factory control structures, potential tools and standards for developing agent-based manufacturing systems. An extensive annotated bibliography is provided.
The authors look at how `holonic' thinking may carry the key to devising the flexible, infinitely adaptable manufacturing systems that the `agile' enterprise of the 21st century will need
In simple terms, one can say that team coaching in adversarial domains consists of providing advice to distributed players to help the team to respond eectively to an adversary. We have been researching this problem to nd that creating an autonomous coach is indeed a very challenging and fascinating endeavor. This paper reports on our extensive empirical study of coaching in simulated robotic soccer. We can view our coach as a special agent in our team. However, our coach is also capable of coaching other teams other than our own, as we use a recently developed universal coach language for simulated robotic soccer with a set of prede ned primitives. We present three methods that extract models from past games and respond to an ongoing game: (i) formation learning, in which the coach captures a team's formation by analyzing logs of past play; (ii) set-play planning, in which the coach uses a model of the adversary to direct the players to execute a speci c plan; (iii) passing rule learning, in which the coach learns clusters in space and conditions that de ne passing behaviors. We discuss these techniques within the context of experimental results with dierent teams. We show that the techniques can impact the performance of teams and our results further illustrate the complexity of the coaching problem.
The concept of an agent has recently become important in Artificial Intelligence (AI), and its relatively youthful subfield, Distributed AI (DAI). Our aim in this paper is to point the reader at what we perceive to be the most important theoretical and practical issues associated with the design and construction of intelligent agents. For convenience, we divide the area into three themes (though as the reader will see, these divisions are at times somewhat arbitrary). Agent theory is concerned with the question of what an agent is, and the use of mathematical formalisms for representing and reasoning about the properties of agents. Agent architectures can be thought of as software engineering models of agents; researchers in this area are primarily concerned with the problem of constructing software or hardware systems that will satisfy the properties specified by agent theorists. Finally, agent languages are software systems for programming and experimenting with agents; the...
In multiagent domains with adversarial and cooperative agents, team agents should be adaptive to the current environment and opponent. We introduce an online method to provide the agents with team plans that a "coach" agent generates in response to the specific opponents. The coach agent is equipped with a number of pre-defined opponent models. The coach is then able to quickly select between different models online by using a naive Bayes style algorithm, making the planning adaptive to the current adversary. The coach uses a Simple Temporal Network to represent team plans as coordinated movements among the multiple agents and it searches for an opponent-dependent plan for its teammates. This plan is then communicated to the agents, who execute the plan in a distributed fashion. The system is fully implemented in a simulated robotic soccer domain.
In intelligent agent software engineering. Cooperation Between Agents to Evolve Complete Programs, Valentina Plekhanova. University of Sunder-land, United Kingdom
- R Aler
- D Camacho
- A Moscardini
Aler, R., Camacho, D., Moscardini, A., 2003. In intelligent agent software engineering. Cooperation Between Agents to Evolve Complete Programs, Valentina Plekhanova. University of Sunder-land, United Kingdom. Idea Group Publishing, pp. 213–228.
The evolution of the CooperA platform. Foundations of Distributed Artificial Intelligence
- L Sommaruga
- N M Avouris
- M V Liedekerke