Abstract
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 with nonprehensile manipulation. To study nonprehensile manipulation, we studied robotic batting, a primitive form of nonprehensile manipulation. Batting is a challenging research area because it requires sophisticated and fast manipulation of moving objects and requires considerable improvement. In this paper, we designed a batting system for dynamic manipulation of a moving ball and proposed several algorithms to improve the task performance of batting. To improve the recognition accuracy of the ball, we proposed a circle-fitting method that complements color segmentation. This method enabled robust ball recognition against illumination. To accurately estimate the trajectory of the recognized ball, weighted least-squares regression considering the accuracy according to the distance of a stereo vision sensor was used for trajectory estimation, which enabled more accurate and faster trajectory estimation of the ball. Further, we analyzed the factors influencing the success rate of ball direction control and applied a constant posture control method to improve the success rate. Through the proposed methods, the ball direction control performance is improved.
Highlights
Published: 26 April 2021To date, a variety of robots have been used in automated production lines for object manipulation tasks in factories, and these robotic technologies have contributed significantly to the development of modern industry
By maindirection control is decreased. To compensate this time error, we propose a method of maintaining the posture of the end-effector for a for predetermined time before and after taining the posture of the end-effector for a predetermined time before and after the hitmaintaining the posture of the end-effector for a predetermined time before and the ball hitting, and this method is called the constant posture control (CPC) method
In terms of object recognition, applied a circular fitting method thatthat is robust to the influence of illuminance and and imwe applied a circular fitting method is robust to the influence of illuminance proved the position accuracy of the ball by about compared to the conventional improved the 3D position accuracy of the ball by about 60% compared to the conventional image method with with color color segmentation segmentation and and noise noise filtering filtering applied
Summary
Published: 26 April 2021To date, a variety of robots have been used in automated production lines for object manipulation tasks in factories, and these robotic technologies have contributed significantly to the development of modern industry. With the fourth industrial revolution, robots have been introduced to provide various services in factories and in human living environments. Robots used in factories perform simple repetitive operations such as pick-and-place using specially designed grippers; in an environment such as cafes and restaurants, human-level object manipulation ability is required. To provide a wider range of services in a human living environment, robots must have a higher level of object manipulation similar to that of humans. A robot that performs nonprehensile manipulation is rare owing to the difficulty of control using nonprehensile manipulations. When nonprehensile manipulation is performed, the object moves during manipulation. Since the moving object is not fixed to the robot, it is necessary to plan and control the future behavior
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
