Journal of System Simulation ›› 2017, Vol. 29 ›› Issue (8): 1736-1747.doi: 10.16182/j.issn1004731x.joss.201708013

Previous Articles     Next Articles

Research on Picking Robot Vision Localization Based on Semi-physical Simulation

Chen Keyin1,2, Zou Xiangjun3*, Peng Hongxing3, Liang Haiying4, Hu Yuanchuang4   

  1. 1. School of Information and Communication Engineering, Hezhou University, Hezhou 542899, China;
    2. Nanjing Institute of Agricultural Mechanization, Ministry of Agriculture, Nanjing 210014, China;
    3. Key Lab of Key Technology of South Agricultural Machine and Equipment Ministry of Education, South China Agricultural University, Guangzhou 510642, China;
    4. School of Mathematics and Computer Science, Hezhou University, Hezhou 542899, China
  • Received:2016-09-09 Published:2020-06-01

Abstract: Aiming at the problems of accuracy and stability of the vision localization based on physical picking robot, which were easy to make mistakes, long cycle, and not easy to be carried out indoors, a picking robot vision localization method based on the semi-physical simulation technology was proposed combining with the robot vision localization mechanism and robot kinematics. This method adopted the virtual picking robot to instead of the physical robot, and studied the vision localization of the fruit target in the virtual simulated environment, which was as the vision localization based on semi-physical simulation. The test results show that: the average absolute error and relative error of the target fruit are only about 2.89 mm and 0.43% in the vision localization simulated environment, which is in line with the accuracy requirements of the actual vision localization, so the effectiveness and feasibility of this simulation method are validated.

Key words: the picking robot, vision localization, robot kinematics, semi-physical simulation

CLC Number: