A modified eye‐in‐hand stereo visual control for grasping unknown objects via Scara robot

Abstract Here, the switch proportional integral derivative controller (PID) stereo image‐based visual servoing controller is designed for controlling the manipulator robots. The proposed control algorithm separates the rotational and translational motion of the camera, so the stereo image‐based visual servoing control could be decomposed into three separate stages with different gains. Despite the increasing computation and complexity of relationships, instead of kinematics, robot dynamics are used to guide the robot to make the simulation more consistent with the real condition. To reduce response time and improve the robot's trajectory, the object positions in the image space are predicted by the Extended Kalman filter. The results showed that the proposed method produces a more accurate response than the classical methods that use robot kinematics. Adding the trajectory estimation algorithm improves the time response of the system and its industrial application capabilities.