Search

Different view point clouds of objects can be achieved through machine vision and need to be translated into a coherent coordinate system for registration. To reduce the number of iterations of accurate registration algorithm and avoid local optical algorithm, coarse registration can provide the initial value of good posture for precise registration. For solving the issues, we proposed a practical coarse registration method of point clouds based on image feature points. In the proposed method, 3D feature point detection methods were respectively established based on dense point clouds derived from monocular structured light vision according to 2D feature points detected by using Speeded Up Robust Features (SURF) algorithm. Through the combination of rigid body posture measurement method and removing method of gross error points, the precise rotation matrix and translation vector before and after moving point clouds were obtained. In the experiment, we introduced the method of dense point clouds derived from structured light in detail. The experimental results indicated that the method could provide good initial postures for precise registration of point clouds.

There are many possible trajectories between the given points in Euclidean geometry space for industrial robots. Under constraints of robotic kinematics or dynamics, the optimization of robotic running time is required. In this paper, a trajectory planning method of robot based on quantum genetic algorithm is proposed. Firstly, cubic B-spline function and constraint condition of robotic kinematics were introduced. Then, the chromosome and evolutionary update strategy in quantum genetic algorithm were described, and the variable fitness function of trajectory planning was also defined. Finally, the methods and procedures were introduced in detail, and the first three joint trajectories and the quantum genetic algorithm were programmed on MATLAB platform. The simulation experiments showed that trajectories of joint displacement, velocity, acceleration and jerk could be obtained effectively. The results verified the reliability and practicability of the method.

Industrial robots have been widely applied in grasping static workpieces, but the measurement method for the three-dimensional position of known specifications and random location of online workpieces still cannot meet the application requirements of the industrial field. In this paper, system structure and installation design of hardware were introduced firstly. Then, image pre-processing and feature extraction were established, composing of image enhancement, image smooth, edge detection, corner detection and angle calculation. Finally, a monocular vision-guided robot grasping device platform was established as well as corresponding software control platform. Experimental results indicated that the monocular vision system could quickly identify the workpiece pose with high measurement accuracy and that the robot could successfully grasp random location workpieces.