A multi-agent collaborative control architecture with fuzzy adjustment for a mobile robot

Conference Paper · January 2006with2 Reads
Source: DBLP
Conference: ICINCO 2006, Proceedings of the Third International Conference on Informatics in Control, Automation and Robotics, Robotics and Automation, Setúbal, Portugal, August 1-5, 2006

One of the current challenges of control research is to make systems capable of showing intelligent responses to changing circumstances. To address this task, more complex systems are being developed. However, it is technologically difficult and potentially dangerous to build complex systems that are controlled in a completely centralized way. One approach to building decentralization systems is using multi-agent technology for building control architectures. But it seems risky to recursively extend using multi-agent systems to develop part of the system, such as a single behaviour.One alternative approach is to use collaborative control to deploy specific (low level) behaviours, so that several controllers are combined in a single agent of the multi-agent architecture in order to achieve the wanted behaviour. This paper presents a collaborative controller applied to the goto behaviour. The experiments were carried out using a Pioneer mobile robot.

    • "This agent is getting the control regarding to the conflicting activity. For example, suppose that the goto agent has a utility value of 0.5, the gothrough agent of 0.3 and the avoid agent of 0.7; being 0.7 the higher value, the avoid agent takes the control of the situation, and it is the only one that sends messages to the robot agent (see [21, 22]). In order to reduce communication among agents, the last agent who has had the control, broadcasts it utility value. "
    [Show abstract] [Hide abstract] ABSTRACT: This chapter reviews different approaches for the development of new models, architectures and real applications of physical agents. The chapter starts by identifying this kind of agents and their main requirements. After that, it presents one approach to allow deliberation while the world changes, and some specific applications that have been implemented by different participants of the AgentCities.ES network: a multi-agent system architecture to control a single robot, a submarine robot, and a container terminal management system for the port of Valencia.
    Full-text · Chapter · Dec 2007