Evolutionary Learning for Fuzzy Path Planning of Shooting Action for Robot Soccer
نویسندگان
چکیده
This paper proposes a new selection mechanism in evolutionary learning for fuzzy systems, which is applied to the learning of shooting action for robot soccer. In generic evolutionary algorithm, since the evaluation and the selection are performed on the level of chromosome, selected chromosome may include non-effective or bad genes, which increase the uncertainty of the solutions. To solve this problem, we propose a rule-scoring method for selection on the level of gene, which grades genes at the same position in the chromosomes. The method is applied to fuzzy path planner for shooting action of soccer robot, in which each fuzzy rule is encoded as a gene. Simulation results show the effectiveness and the applicability of the proposed method.
منابع مشابه
Study of Evolutionary and Swarm Intelligent Techniques for Soccer Robot Path Planning
Finding an optimal path for a robot in a soccer field involves different parameters such as the positions of the robot, positions of the obstacles, etc. Due to simplicity and smoothness of Ferguson Spline, it has been employed for path planning between arbitrary points on the field in many research teams. In order to optimize the parameters of Ferguson Spline some evolutionary or intelligent al...
متن کاملA Selection Scheme for Excluding Defective Rules of Evolutionary Fuzzy Path Planning
This paper proposes a new selection mechanism in evolutionary algorithm for fuzzy systems that can be applied to robot learning of shooting ability in robot soccer. In generic evolutionary algorithms, evaluation and selection are performed on the chromosome level, where a selected chromosome may include non-effective or bad genes. This may lead to an increase in the uncertainty of the solutions...
متن کاملFuzzy Logic Controller for Shooting Action of an Integrated Multi-agent Robot System
An integrated multi-agent robot system for robot soccer games consists of multiple mobile robots, a vision system, a wireless communications system and a host computer. The multiple robots can be cooperatively controlled as they play a robot soccer game in an unknown and dynamic environment. The development of the system involved mechanism design and manufacture, integration of the electromecha...
متن کاملA Method for Obstacle Avoidance and Shooting Action of the Robot Soccer
In this paper, a Fuzzy-Obstacle-Avoidance-Path (FOAP) algorithm for the obstacle avoidance and a procedure for the shooting action of the robot soccer based on this algorithm are proposed. This algorithm contains a fuzzy system that is used to estimate the rotational velocity of the robot soccer. To demonstrate the effectiveness and applicability of the proposed method, two simulations are pres...
متن کاملRecombinant Rule Selection in Evolutionary Algorithm for Fuzzy Path Planner of Robot Soccer
A rule selection scheme of evolutionary algorithm is proposed to design fuzzy path planner for shooting ability in robot soccer. The fuzzy logic is good for the system that works with ambiguous information. Evolutionary algorithm is employed to deal with difficulty and tediousness in deriving fuzzy control rules. Generic evolutionary algorithm, however, evaluate and select chromosomes which may...
متن کامل