Conference Paper

All Bids for One and One Does for All: Market-Driven Multi-agent Collaboration in Robot Soccer Domain.

DOI: 10.1007/978-3-540-39737-3_66 Conference: Computer and Information Sciences - ISCIS 2003, 18th International Symposium, Antalya, Turkey, November 3-5, 2003, Proceedings
Source: DBLP

ABSTRACT In this paper, a novel market-driven collaborative task allocation algorithm called “Collaboration by competition / cooperation”
for the robot soccer domain is proposed and implemented. In robot soccer, two teams of robots compete with each other to win
the match. For the benefit of the team, the robots should work collaboratively, whenever possible. The market-driven approach
applies the basic properties of free market economy to a team of robots for increasing the profit of the team as much as possible.
The experimental results show that the approach is robust and flexible and the developed team is more succcessful than its

KeywordsMarket-driven-multi-agent-collaboration-robot soccer

  • [Show abstract] [Hide abstract]
    ABSTRACT: This survey paper starts with a basic explanation about robot soccer and its systems, then will focus on the strategies that have been used by previous researchers. There is a time-line of described robot soccer strategies, which will show the trend of strategies and technologies. The basic algorithm for each robot, that is described here, morphs from just simple mechanical maneuvering strategies to biologically inspired strategies. These strategies are adapted from many realms. The realm of educational psychology, produced reinforcement learning and Q-learning, commerce produced concepts of market-driven economy, engineering with its potential field, AI with its petri-nets, neural network and fuzzy logic. Even insect and fish were simulated in PSO and have been adapted into robot soccer. All these strategies are surveyed in this paper. Another aspect surveyed here is the vision system trend that is shifting from global vision, to local omni-directional vision, to front-facing local vision, which shows the evolution is towards biologically inspired robot soccer agent, the human soccer player.
    Artificial Intelligence Review 10/2013; · 1.57 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: Having in mind, that both humans and machines are limited in their ability to perceive the real world in its complexity, our research was primarily oriented on better understanding of how decisions in different contexts are formed, how decision makers deal with incompleteness, inaccuracy or inconsistency of information. The book is bringing partial knowledge about decision making processes in autonomous systems from different points of view, and is organized as follows: In Chapter 1, an innovative and flexible soft computing technique based on Grey Systems Theory and Fuzzy Cognitive Maps called Fuzzy Grey Cognitive Maps (FGCM) is proposed. FGCM offer several advantages in comparison to other similar techniques. First, the FGCM model is defined specifically for multiple meanings (grey) environments. Second, FGCM allow the defining of relationships between concepts. Through this characteristic, decisional models that are more reliable for interrelated environments are defined. Third, FGCMs are able to quantify the grey influence of the relationships between concepts. Through this attribute, a better support in grey environments can be reached. Finally, with this FGCM model it is possible to develop a what-if analysis with the purpose of describing possible grey scenarios. Chapter 2 describes three selected theoretical problem areas of automated trading systems (ATS) design. First part is focused on ATS lifecycle, describing typical stages of its development and application in trading practice. Second part is focused on application of fundamental analysis in commodity trading which is source of important information based on other principles that most commonly used technical analysis. Spread trading is used here as a demonstration of alternative to standard futures trading. Commodities tend to behave in seasonal patterns and comprehensible trading approach using seasonal trading strategies will be described as well in the second part. Third part describes intended future work in area of automated trading. In this part is presented description of multiagent systems (MAS) used for coordination of trading effort. Multiple trading systems are traded at the same time using this MAS. Contract net protocol is used for cooperation in proposed MAS. Third part is theoretical but reflects modern trends of trading leading towards more intense automation of trading processes. The coalition formation is a widely used form of cooperation of artificial intelligent agents in multi-agent systems. Chapter 3 investigates relevancy of usage of properties and mechanisms of the biological immune system in the multi-agent coalition formation. Requirements for the effective multi-agent coalition formation are specified based on the behaviour of the human biological immune system. Chapter 4 deals with description of means for decision-making in mobile robotics as well as some integrated decision-making systems. They are mostly oriented to applications in robotic soccer because it enables to solve a number of robotic problems from optimal control of individual actuators up to constructing complex multiagent systems for teams of robots. The spectrum of nowadays decision-making means that are used in robotics is much spread and it is not possible to mention them all. Therefore, there are described only such means that seems to be perspective for their use in robotic decision-making processes like naïve Bayes classifiers, decision trees, Markov decision processes and fuzzy cognitive maps. Practical application of automated trading system requires extensive testing and background knowledge of principles of used tools. Especially technical analysis indicators, which are considered to be basic instrument for designing automated (mechanical) trading systems, may be optimized or modified to serve individual trader’s needs. Also, each market environment is specific and identical indicators work differently and with various results in different markets. Chapter 5 is focused on testing and optimization of technical analysis tools from the perspective of designing automated trading system for small speculator use on commodity markets, as well as testing of application of selected exit strategies on automated trading system’s performance. Decision making support by multi-criteria models with evaluation of trends is presented in Chapter 6. The recently developed method of Cognitive Hierarchy Process (CHP) is applied to find the optimal offer with respect to customers’ needs and expectations. Data based on individual preferences are used for modification of parameters of the model. Various segments of customers found by cluster analysis are considered. Prevailing trends in customers’ behavior are reflected in trends for individual clusters, thus enabling prediction of the future customers’ preferences. Agent is generally defined as an autonomous entity, able to response to stimuli from the environment and optionally to perform goal-oriented actions. Chapter 7 is focused on explanation of agent-based simulations’ research approach. NetLogo programming environment is presented in general and two implementations of iterated prisoner’s dilemma are shown. The experimenting in BehaviorSpace utility is also described. Multi-agent modelling and simulations are frequently used in research and development in different types of scientific disciplines. The quality of multi-agent model depends on various factors. The precise analysis and design of multi-agent model is one of them. The multi-agent model should be developed systematically and deeply to facilitate its implementation with the aid of the specific programming language. Chapter 8 deals with the design of the framework that can be used for systematic development of multi-agent models. Chapter 9 deals with recent activities in the area of smart offices and other smart workplaces, but also with an interesting area of large-scale applications of Ambient Intelligence (AmI). The first subchapter focuses on recent AmI applications on the way towards really smart workplaces. The second subchapter mentions some possibilities for so-called large-scale ambient intelligence that is a way how to use the idea of AmI in outdoor large-scale conditions. The chapter is concluded by a discussion about possible research directions in the area of smart workplaces and large-scale AmI. Fast technological progress enables people to work anywhere and at anytime in real space with the help of ICT technologies. The use of virtual teams presented in Chapter 10 followed a development of the teamwork whose massive breakthrough was at the turn of 1980s and 1990s with the introduction of TQM. In the mid 1990s, owing to the technological development and growing globalization, companies started to strengthen international teams and introduce global ways of human resources management. Chapter 11 describes selected problem areas of economic and investment games and simulators used in education, training and research. First part, theoretical, is focused on conditions and significant factors of playing games and simulators. Second part is focused on the description of five selected simulators. Third part brings results of research and description of eleven economic games that are covering the field of financial and managerial accounting and related areas, for example management and logistics.
    edited by Libor Kubica, 01/2011; BEN, Praha., ISBN: 978-80-7300-415-6
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: In cooperative multi-agent systems, roles are used as a design concept when creating large systems, they are known to facilitate specialization of agents, and they can help to reduce interference in multi-robot domains. The types of tasks that the agents are asked to solve and the communicative capabilities of the agents significantly affect the way roles are used in cooperative multi-agent systems. Along with a discussion of these issues about roles in multi-agent systems, this article compares computational models of the role allocation problem, presents the notion of explicitly versus implicitly defined roles, gives a survey of the methods used to approach role allocation problems, and concludes with a list of open research questions related to roles in multi-agent systems.
    Autonomous Agents and Multi-Agent Systems 01/2011; 22:317-355. · 0.79 Impact Factor

Full-text (4 Sources)

Available from
Jun 10, 2014