Takahiro Kitajima

Correction method of wind speed prediction system using predicted wind speed fluctuation

This paper describes a prediction of a wind speed fluctuation by using hierarchical neural network to improve the wind speed prediction. The future wind speed fluctuation (increase or decrease) is predicted with discrete value (1 or -1). The timing of the wind speed changes after 10 minutes is predicted. Time delay is confirmed during the predicted and observed values. Therefore, the timing of wind speed change is focused. Besides, the correction system of the wind speed prediction by using the fluctuation prediction result is proposed where two types of correction methods are applied. The wind speed prediction by applying RMSE method in the existence/absence of correction is evaluated. Finally, the application limit of correction when using fluctuation prediction result and effectiveness of predicting the wind speed fluctuation also will be considered.

Multiple Vehicles Semi-Self-driving System Using GNSS Coordinate Tracking under Relative Position with Correction Algorithm

This paper describes a simple and low-cost semiself- driving system which is constructed without cameras or image processing. In addition, a position correction method is presented by using a vehicle dynamics. Conventionally, selfdriving vehicle is operated by various expensive environmental recognition sensors. It results in rise in prices of the vehicle, and also the complicated system with various sensors tends to be a high possibility of malfunction. Therefore, we propose the semi-self-driving system with a single type of global navigation satellite system (GNSS) receiver and a digital compass, which is based on a concept of a preceding vehicle controlled by a human manually and following vehicles which track to the preceding vehicle automatically. Each vehicle corrects coordinate using current velocity and heading angle from sensors. Several experimental and simulation results using our developed smallscale vehicles demonstrate the validity of the proposed system and correction method.

Object Conveyance Algorithm for Multiple Mobile Robots based on Object Shape and Size

This paper describes a determination method of a number of a team for multiple mobile robot object conveyance. The number of robot on multiple mobile robot systems is the factor of complexity on robots formation and motion control. In our previous research, we verified the use of the complex-valued neural network for controlling multiple mobile robots in object conveyance problem. Though it is a significant issue to develop effective determination team member for multiple mobile robot object conveyance, few studies have been done on it. Therefore, we propose an algorithm for determining the number of the team member on multiple mobile robot object conveyance with grasping push. The team member is determined based on object weight to obtain appropriate formation. First, the object shape and size measurement is carried out by a surveyor robot that approaches and surrounds the object. During surrounding the object, the surveyor robot measures its distance to the object and records for estimating the object shape and size. Since the object shape and size are estimated, the surveyor robot makes initial push position on the estimated push point and calls additional robots for cooperative push. The algorithm is validated in several computer simulations with varying object shape and size. As a result, the proposed algorithm is promising for minimizing the number of the robot on multiple mobile robot object conveyance.