Fuzzy Potential Method Research Articles

Self-driving Electric Wheelchair in Crowded Environments Using a Fuzzy Potential Model Predictive Control

In the recent development of small autonomous vehicles, such as electric wheelchairs, one of the challenging environments to be operated is a congested area in which vehicles are mixed with pedestrians. In addition to prompt avoidance in response to the surrounding non-stationary environment, optimal maneuvering must be conducted between the multiple feasible trajectories. In the present study, the fuzzy potential method is combined with model predictive control to avoid obstacles based on predictions of future behavior. Furthermore, the global search for a solution and flexible switching of avoidance paths were achieved utilizing the Monte Carlo optimization in model predictive control. This also enables the optimization of a nonlinear and discontinuous evaluation function including membership functions for fuzzy inference. The method's effectiveness was verified through simulations and real-time experiments for a self-driving electric wheelchair equipped with a LiDAR, and verification confirmed flexible obstacle avoidance.

自律全方位移動ロボットの並進と回転の同時制御によるロボットサイズを考慮した障害物回避(機械力学,計測,自動制御)

This paper presents a real time collision avoidance method considering robot's size for an autonomous omni-directional mobile robot by simultaneous control of translational and rotational motions. This method enables the robot, which the size of width is not equal to that of length, to avoid unknown obstacles safely and efficiently in real time. To consider the difference between the width and length of the robot, the Capsule Case is newly introduced. In order to achieve the simultaneous control, this method employs an omni-directional platform. As an example of design method of the proposed method, novel control method based on the Fuzzy Potential Method is proposed. To verify the effectiveness of the proposed method, several numerical simulations and experiments are carried out.

1A1-A24 自律全方位移動ロボットの拡張ファジィポテンシャル法を用いた移動物体を考慮した行動制御(動作計画と制御の新展開)

The respective autonomous mobile robots need to recognize the changes in the environment accurately to accomplish the tasks effectively. In order to realize that, it is significant to predict the movements of the surrounding obstacles. This study proposes a prediction method of the moving objects of the robot's surroundings. The method uses only the information from the sensors on the robot, and thereby can be applied to many kinds of autonomous mobile robots without path planning and self-localization. At first, this paper introduces a method that the robot can estimate moving objects velocity, position, and own velocity. In addition, this paper proposes a method which can control the autonomous mobile robots' behavior using the extended fuzzy potential method from the prediction results. The effectiveness of the method was verified by using the soccer robots of RoboCup Middle-Size-League.