Velocity and direction planning in a sumo robot type using the method of potential field with fuzzy systems

摘要

An application of the potential field method is presented in this paper for autonomous sumo robot class navigation with dynamic environments including moving target and static obstacle. The method used in this paper aims to planning the velocity and the direction taken by the robot in order to reach your target in the possible shortest time. The design velocity is determined from the relative velocities between the robot and the target as well as the relative positions between them. This work uses a hybrid method to determine the velocity and position of a sumo robot class, which is intended to push the opponent out of the arena. This hybrid method applies the potential field with fuzzy logic and use the Mamdani model to obtain the necessary variables for determining the velocity and direction to be followed by the robot. For determining the time necessary to find the target two simulations were done in the MATLAB. The obtained results show that the hybrid method overcomes the local minimum problem within any stationary or dynamic environment with static obstacles.