Object pose estimation for grasping based on robust center point detection

The objective of this study is to design a grasping system for a mobile manipulator, such that it can find and grasp a target object using vision. Speed up robust feature (SURF) algorithm was adopted to define features of the target object and match features between current image and object database to confirm the target. To strengthen the feature matching results and calculate the necessary reference control point, we adopted RANdom Sample Consensus (RANSAC) algorithm to estimate the planar transformation matrix (Homography matrix) in order to accurately mark the center of target. A control design was developed based-on coordinate estimation for visual servoing of the mobile manipulator. Experiments on a self-constructed mobile manipulator reveal that the proposed method can find and grasp a target object successfully.