3D Grasp Planning using Stereo Matching and Neural Network

스테레오정합과 신경망을 이용한 3차원 잡기계획

  • 이현기 (경북대학교 기계공학과) ;
  • 배준영 (경북대학교 대학원 기계공학과) ;
  • 이상룡 (경북대학교 기계공학부)
  • Published : 2003.07.01


This paper deals with the synthesis of the 3-dimensional grasp planning for unknown objects. Previous studies have many problems, which the estimation time for finding the grasping points is much long and the analysis used the not-perfect 3-dimensional modeling. To overcome these limitations in this paper new algorithm is proposed, which algorithm is achieved by two steps. First step is to find the whole 3-dimensional geometrical modeling for unknown objects by using stereo matching. Second step is to find the optimal grasping points for unknown objects by using the neural network trained by the result of optimization using genetic algorithm. The algorithm is verified by computer simulation, comparing the result between neural network and optimization.


Stereo Matching;Neural Network;Grasp Planning


  1. Kim, G B., Chung, S. C., 2001, 'A Stereo Matching Algorithm with Projective Distortion of Variable Windows,' Transactions of KSME, A, Vol. 25, No.3, pp.461-469
  2. Park, K., 1999, '3D Object Recognition and Accurate Pose Calculation Using a Neural Network,' Transactions of KSME, A, Vol. 23, No. 11, pp. 1929-1939
  3. Zhang, Z., 1999, 'Flexible Camera Calibration by Viewing a Plane from Unknown Orientations,' In Proc. 7th International Conference on Computer Vision, Kerkyra, Greece, pp. 666-673
  4. HeikkiHi, J., and Silveri, 0., 1997, 'A Four-step Camera Calibration Procedure with Implicit Image Correction,' In IEEE Computer Society Conference on Computer Vision and Pattern Recognition(CVRP'97), San Juan, Puerto Rico, pp. 1106-1112
  5. Hyun-Hyup Lee and Kyung-Il Mun, 'Fuzzy-Neuro by using a MATLAB,' Ajin Press
  6. Maybank, S. J., and Faugeras, O., 1992, 'A Theory of Self-Calibration of a Moving Camera,' International Journal of computer Vision, 8(2): 123-151
  7. Zhang, Z., 1998, 'A Flexible New Technique for Camera Calibration,' Technical Report MSRTR-98-71, Microsoft Research
  8. Hyun-Ki Lee, Myun-Hee Kim and Sang-Ryong Lee, 2002, 'Optimization of 3D Grasping Points with Whole 3D Modeling for Unknown Object,' In Proc. Of the 2nd China-Korea Joint Workshop on Robotics, Shenyang, China
  9. Fusiello, A., Trucco, E., and Verri, A., 2000, 'A Compact Algorithm for Rectification of Stereo Pairs,' Machine Vision and Applications, 12(1): 16-22
  10. Laszlo, J., 'Computational Geometry and computer graphics in C++,' Prentice Hall Press
  11. Morales, A., Recattala, G, Pedro J. Sanz, and Angel P. del Pobil, 2001, 'Heuristic Vision-Based Computation of Planar Antipodal Grasps on Unknown Objects,' In Proceeding of the IEEE International Conference on Robotic & Automation, Seoul, Korea
  12. Borst, Ch., Fischer, M., and Hirzinger, G, 1999, 'A Fast and Robust Grasp Planner for Arbitary 3D Objects,' In Proc. of IEEE International Conference on Robotics & Automation, Detroit, Michigan
  13. Ferrari, C., and Canny, J., 1992, 'Planning Optimal Grasps,' In Proceeding of the IEEE International Conference on Robotics & Automation, pp. 2290-2295, Nice, France
  14. Katada, Y., Svinin, M., Ohkura, K., and Ueda, K., 2001, 'Optimization of Stable Grasps by Evolutionary Programming,' In Proceeding of the 32nd ISR
  15. Nguyen, V.-D., 1988, 'Constructing force-closure grasps,' The International Journal of Robotics Research, 7(3)
  16. Hauck, A., Ruttinger, J., Sorg, M., and Farber, G, 1999, 'Visual Determination of 3D Grasping Points on Unknown Objects with a Binocular Camera System,' In Proceeding of the IEEE/RSJ International Conference on Intelligent robots and System, pp. 272-278