期刊名称：International Journal of Advanced Robotic Systems
印刷版ISSN：1729-8806
电子版ISSN：1729-8814
出版年度：2017
卷号：14
期号：5
DOI：10.1177/1729881417734829
出版社：SAGE Publications
摘要：The real-time calculations of the positioning error, error correction, and state analysis have always been a difficult challenge in the process of autonomous positioning. In order to solve this problem, a simple depth imaging equipment (Kinect) is used, and a particle filter based on three-frame subtraction to capture the end-effector’s motion is proposed in this article. Further, a back-propagation neural network is adopted to recognize targets. The point cloud library technology is used to collect the space coordinates of the end-effector and target. Finally, a three-dimensional mesh simplification algorithm based on the density analysis and average distance between points is proposed to carry out data compression. Accordingly, the target point cloud is fitted quickly. The experiments conducted in the article demonstrate that the proposed algorithm can detect and track the end-effector in real time. The recognition rate of 99% is achieved for a cylindrical object. The geometric center of all particles is regarded as the end-effector’s center. Furthermore, the gradual convergence of the end-effector center to the target centroid shows that the autonomous positioning is successful. Compared to traditional algorithms, both moving the end-effector and a stationary object can be extracted from image frames using a thesis. The thesis presents a simple and convenient positioning method, which adjusts the motion of the manipulator according to the error between the end-effector’s center and target centroid. The computational complexity is reduced and the camera calibration is eliminated.
关键词：Autonomous positioning ; particle filter ; manipulator ; BP neural network ; point cloud library
