Abstract | ||
---|---|---|
Autonomous grasping in dynamic and unstructured environments is challenging in robotics. We aim to solve the problem by proposing an grasping algorithm for unknown objects based on adaptive dynamic force balance. Firstly, Principal Component Analysis(PCA) is used to adjust the axis direction of the camera coordinate system, so that it is consistent with the object coordinate system. The multi-plane projection policy and contour detection algorithm are used to extract the 2D contour information of unknown object, which can reduce the computational complexity. Secondly, a graspable area generating algorithm is established by estimating the size of target object and the distance of the gripper. Several candidate areas are adaptively generated by detecting the concave and convex points on the edge. The optimal grasping area is dynamically selected by minimizing the angle obtained from force balance analysis. The grasping pose is generated by using the depth image to complete autonomous grasping operation. In order to verify the effectiveness of proposed algorithm, a 6-DoF robot grasping platform is built based on eye-in-hand calibration. The experimental results show that compared with the current grasping algorithms, the proposed algorithm can effectively obtain the optimal grasping area of unknown objects without GPUs, which can achieve higher execution efficiency and adaptability. |
Year | DOI | Venue |
---|---|---|
2022 | 10.1007/s10846-021-01546-4 | Journal of Intelligent & Robotic Systems |
Keywords | DocType | Volume |
Unknown object, Adaptive dynamic force balance, Optimal grasping area, 6-DOF grasping | Journal | 105 |
Issue | ISSN | Citations |
1 | 0921-0296 | 0 |
PageRank | References | Authors |
0.34 | 11 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
He Cao | 1 | 0 | 0.34 |
Yunzhou Zhang | 2 | 219 | 30.98 |
Guoji Shen | 3 | 0 | 0.34 |
Yanli Shang | 4 | 0 | 0.34 |
Xi Chen | 5 | 333 | 70.76 |