| Summary: | 碩士 === 長庚大學 === 機械工程研究所 === 95 === Middle size soccer robot is a real time and dynamic control system, and it is capable of dealing with complicated competition environment in terms of advanced artificial intelligence. In general, the middle size soccer robot is composed of the modules of the vision, path planning, motion control, and mechanical and driving robot body. In this work, the kinematics and dynamics of ball and robot are modeled to assist the fuzzy based decision system. In this manner, the decision of robot path planning is inferred from static ball location to the dynamically estimated ball path. Consequently, the proposed decision system is capable of predicting ball motion and then deciding the kick location, velocity and direction. Therefore, the robot moves towards the desired kick location instead of the current ball location. On the other hand, the omni-based image system acts as the positioning module. To propose a more precise positioning system, a zone-dependent multi-curve omni-vision regression algorithm is proposed in this work. Based on the proposed omni-vision regression algorithm, the bias of installing anamorphoscope and the complicated curve function of anamorphoscope can be dealt with as well. Finally, this thesis proposes a high precision omni-vision positioning methodology and a prediction based motion planning algorithm for the moving ball, and these approaches improve the performance of motion decision system in real competition environment.
|
|---|
