• Laser & Optoelectronics Progress
  • Vol. 57, Issue 18, 181508 (2020)
Guanyu Xu*, Hongwei Dong**, Junhao Qian, and Zhenlei Xu
Author Affiliations
  • School of Internet of Things Engineering, Jiangnan University, Wuxi, Jiangsu 214122, China
  • show less
    DOI: 10.3788/LOP57.181508 Cite this Article Set citation alerts
    Guanyu Xu, Hongwei Dong, Junhao Qian, Zhenlei Xu. Pose Estimation Algorithm for Random Bins Based on Point Pair Features[J]. Laser & Optoelectronics Progress, 2020, 57(18): 181508 Copy Citation Text show less
    Flow chart of pose estimation algorithm based on point pair features
    Fig. 1. Flow chart of pose estimation algorithm based on point pair features
    Diagram of point pair feature
    Fig. 2. Diagram of point pair feature
    Diagram of building a Hash table
    Fig. 3. Diagram of building a Hash table
    Diagram of local coordinates
    Fig. 4. Diagram of local coordinates
    Diagram of voting process
    Fig. 5. Diagram of voting process
    Diagram of consistency adjustment of point cloud normal direction. (a) Original point clouds; (b) point cloud normal direction before adjustment; (c) point cloud normal direction after adjustment
    Fig. 6. Diagram of consistency adjustment of point cloud normal direction. (a) Original point clouds; (b) point cloud normal direction before adjustment; (c) point cloud normal direction after adjustment
    Diagram of gripping pose strategy adjustment. (a) Objects to be gripped; (b) top 5 proposed poses; (c) output poses
    Fig. 7. Diagram of gripping pose strategy adjustment. (a) Objects to be gripped; (b) top 5 proposed poses; (c) output poses
    Diagram of adjustment of angle deviation caused by rotational symmetry
    Fig. 8. Diagram of adjustment of angle deviation caused by rotational symmetry
    Diagrams of gripping system. (a) Simulation environment; (b) real environment
    Fig. 9. Diagrams of gripping system. (a) Simulation environment; (b) real environment
    Diagrams of pose estimation. (a) Simulation environment; (b) real environment
    Fig. 10. Diagrams of pose estimation. (a) Simulation environment; (b) real environment
    Line charts of pose estimation results. (a) Simulation environment; (b) real environment
    Fig. 11. Line charts of pose estimation results. (a) Simulation environment; (b) real environment
    Statistical resultsSimulation environmentReal environment
    Total number of experiments240240
    Number of successes233182
    Number of failures758
    Success rate /%97.175.8
    First reason for failure is that range of robot is not enough712
    Second reason for failure is that suction of gripper is not enough046
    Table 1. Statistics of gripping success rate in experiments
    Statistical resultsOriginal algorithmMy algorithm
    Number of successes1720
    Number of failures30
    Success rate /%85100
    Fitness /%85.7998.19
    Inlier RMSE (root-mean-square error) /mm0.000680.00032
    Table 2. Statistics of point cloud matching results of simulation data
    Guanyu Xu, Hongwei Dong, Junhao Qian, Zhenlei Xu. Pose Estimation Algorithm for Random Bins Based on Point Pair Features[J]. Laser & Optoelectronics Progress, 2020, 57(18): 181508
    Download Citation