Dynamic Nonprehensile Manipulation of a Moving Object Using a Batting Primitive

To achieve human-level object manipulation capability, a robot must be able to handle objects not only with prehensile manipulation, such as pick-and-place, but also nonprehensile manipulation. study we studied robotic batting, primitive form of Batting is challenging research area because it requires sophisticated and fast moving considerable improvement. In this paper, designed batting system for dynamic ball proposed several algorithms improve the task performance batting. recognition accuracy ball, circle-fitting method that complements color segmentation. This enabled robust against illumination. accurately estimate trajectory recognized weighted least-squares regression considering according distance stereo vision sensor was used estimation, which more accurate faster estimation ball. Further, analyzed factors influencing success rate direction control applied constant posture rate. Through methods, improved.