Abstract. This paper deals with a cooperative control method for a multi-agent system in dynamic environment. This method enables a robot to perform flexible cooperation based on the global evaluation of the achievement of objectives. Each robot communicates qualitative evaluation on the achievement level of each objective. Each robot calculates the global evaluation on the achievement of the team objective from the individual evaluation. The evaluation on the objective achievement is abstracted in order to reduce the influence of variation of the evaluation value and the communication load. As an example, the method is applied to the EIGEN team robots for the Middle Size League of RoboCup, since it is necessary for the soccer robots to cooperate each other in dynamic environment. Its effectiveness was demonstrated through the RoboCup 2004 competition.
Autonomous robots act according to the information they acquire from the environment. However, in real environments, the acquisition of the information regarding an object is often disturbed. This paper deals with the problem of develop an intelligent control for autonomous mobile robots to make them able to adapt to dynamic environment even when the uncertainty of information exists. RoboCup soccer robot is chosen as a demonstration target. In the method we propose, robots extrapolate missing environmental information with short-term memory. However, the acquired or extrapolated information is not always certain. In order to reduce the influences caused by misunderstandings and errors of information, it might be desirable that the robots use qualitative information for the situation where the reliability of information is low. Therefore, in our method, the each robot has an integrator which switches three kinds of action selectors, "Quantitative", "Qualitative" and "Base" according to the reliability index of information. Each action selector operates on some action modules. The action selector selects the action module according to the environmental information. The integrator which is constructed by neural network selects the most suitable action selector based on "Reliability indexes" of the ball position and the self-position estimated with short-term memory. The usefulness of this control system was shown through simulations.
For autonomous mobile robots, visual information is used to recognize the environment. Although the acquisition of visual information is often disturbed in the real environment, it is necessary for a robot to act appropriately even if information is missing. We compensate for missing information for autonomous mobile robots by using short-term memory (STM) to make robots act appropriately. This method involves short-term memory and action selectors. Short-term memory is constructed based on the model of human memory and the forgetting curve used in cognitive science. These action selectors use compensated-for information and determine suitable action. One action selector consists of a neural network whose connection weights are learned by a genetic algorithm. Another selector is designed based on the designer's knowledge. These action selectors are switched based on reliability index of information. RoboCup Middle Size League soccer robots are used for demonstration. The experimental and simulation results show its effectiveness.
Cooperative control is a key issue for multirobot systems in many practical applications. In this paper, we address the problem of coordinating a set of mobile robots in the RoboCup soccer middle size league. We show how the coordination problem that we face can be cast as a specific coalition formation problem and we propose a distributed algorithm to efficiently solve it. Our approach is based on the distributed computation of a measure of satisfaction (called Agent Satisfaction) that each agent computes for each task. We detail how, each agent computes the Agent Satisfaction by acquiring sensor perceptions through an omnidirectional vision system, extracting aggregated information from the acquired perception, and integrating such information with the ones communicated by the team mates. We empirically validate our approach in a simulated scenario and within the RoboCup competitions. The experiments in the simulated scenario allow us to analyse the behaviour of the algorithm in different situations, while the use of the algorithm in the real competitions validates the applicability of our approach to robotic platforms involved in a dynamic and complex scenario.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.