.png){kind=icon}
返回
Unknown Object Grasping Based on Adaptive Dynamic Force Balance
.png){kind=icon}
PRE
AI
DOI：10.1007/s10846-021-01546-4.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
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.
Keyword:
Unknown object
Adaptive dynamic force balance
Optimal grasping area
6-DOF grasping
期刊
J
IF:
2.8
论文数:
3.9K
被引数:
6.9K
机构
引用论文
.png){kind=icon}
A case study on the design and development of minigames for research methods and statistics一项关于为研究方法和统计学设计开发小型游戏（minigames）的案例研究
OAAI
OAAI分享收藏Grasp Pose Detection with Affordance-based Task Constraint Learning in Single-view Point Clouds在单视点云中使用基于可供性的任务约束学习来掌握姿势检测
PREAI
分享收藏High-Performance Pixel-Level Grasp Detection Based on Adaptive Grasping and Grasp-Aware Network
PREAI
分享收藏
查看更多内容