A Modular Neural Network Architecture to Learn the Kinematics of Hand Posture During Grasp

P. Gorce and N. Rezzoug

References

  1. [1] G. Schlesinger, Der mechanische aufbau der kuntstlichenglieder, in M. Borchardt et al. (eds.), Ersatzglieder und Arbeitshilfen fur Kriegsbeschadigte und Unfallverletzte (Berlin: Springer-Verlag, 1919).
  2. [2] J.R. Napier, The prehensile movements of the human hand,Journal of Bone and Joint Surgery, 38, 1956, 902–913.
  3. [3] M.R. Cutkosky, On grasp choice, grasp models, and the designof hands for manufacturing tasks, IEEE Trans. on Roboticsand Automation, 5, 1989, 269–279. doi:10.1109/70.34763
  4. [4] T. Iberall, G. Bingham, & M.A. Arbib, Opposition space as astructuring concept for the analysis of skilled hand movements,Experimental Brain Research, 15, 1986, 158–173.
  5. [5] T. Iberall, Human prehension and dexterous robot hands,International Journal of Robotics Research, 16(3), 1997, 285–299. doi:10.1177/027836499701600302
  6. [6] F. Saito & K. Nagata, Interpretation of grasp and manipulationbased on grasping surfaces, Proc. IEEE Int. Conf. on Roboticsand Automation, Detroit, MI, USA, 1999, 1247–1254. doi:10.1109/ROBOT.1999.772532
  7. [7] R. Tomovic, G.A. Bekey, & W.J. Karplus, A strategy for graspsynthesis with multifingered hand, Proc. IEEE Int. Conf. onRobotics and Automation, Raleigh, NC, USA, 1987, 83–89. doi:10.1109/ROBOT.1987.1087842
  8. [8] G.A. Bekey, H. Liu, R. Tomovic, & W.J. Karplus, Knowledge-based control of grasping in robot hands using heuristics fromhuman motor skills, IEEE Trans. on Robotics and Automation,9 (6), 1993, 709–721. doi:10.1109/70.265915
  9. [9] S.B. Kang & K. Ikeuchi, Toward automatic robot instruc-tion from perception: Mapping human grasps to manipulatorgrasps, IEEE Trans. on Robotics and Automation, 13(1), 1997,81–95. doi:10.1109/70.554349
  10. [10] K. Pook & Ballard, Recognizing teleoperated manipulations,Proc. IEEE Int. Conf. on Robotics and Automation, 2, Atlanta,Georgia, USA, 1993, 578–583.
  11. [11] C. Lee & F.Y. Xu, Online, interactive learning of gestures forhuman/robot interface, Proc. IEEE Int. Conf. on Robotics andAutomation, 4, Minneapolis, MI, USA, 1996, 2982–2987.
  12. [12] M. Becker, E. Kefalea, E. Mael, C. Von der Malsburg, M.Pagel, J. Triesch, J.C. Vorbruggen, R.P. Wurtz, & S. Zadel,GripSee: A gesture-controlled robot for object perception andmanipulation, Autonomous Robots, 6 (2), 1999, 203–221. doi:10.1023/A:1008839628783
  13. [13] M. Jeannerod, The timing of natural prehension, Journal ofMotor Behavior, 13 (3), 1984, 235–254.
  14. [14] C. Bard, J. Troccaz, & G. Vercelli, Shape analysis and handpreshaping for grasping, Proc. IEEE/RSJ Int. Workshop onIntelligent Robots and Systems, Osaka, Japan, 1991, 64–69. doi:10.1109/IROS.1991.174427
  15. [15] D.O. Wren & R.B. Fisher, Dextrous hand grasping strategiesusing preshapes and digit trajectories, Proc. IEEE Int. Conf.on Systems, Man and Cybernetics, 1, Vancouver, BC, Canada,1995, 910–915.
  16. [16] J. Kerr & R. Roth, Analysis of multifingered hands, Interna-tional Journal of Robotics Research, 4, 1986, 3–17. doi:10.1177/027836498600400401
  17. [17] V. Nguyen, Constructing force-closure grasps, Proc. IEEE Int.Conf. on Robotics and Automation, San Francisco, CA, USA,1986, 1368–1373. doi:10.1109/ROBOT.1986.1087483
  18. [18] K. Woelfl & F. Pfeiffer, Grasp strategies for a dextrous robotichand, in V. Graefe (ed.), Intelligent robots and systems (Am-sterdam: Elsevier, 1995).
  19. [19] P. Gorce & J.G. Fontaine, Design methodology for flexiblegrippers, Journal of Intelligent and Robotic Systems, 15(3),1996, 307–328. doi:10.1007/BF00572265
  20. [20] C. Ferrari & J. Canny, Planning optimal grasps, Proc. IEEEInt. Conf. on Robotics and Automation, Nice, France, 1992,2290–2295. doi:10.1109/ROBOT.1992.219918
  21. [21] A.T. Miller & P.K. Allen, Examples of 3D grasps qualitymeasures, Proc. IEEE Int. Conf. on Robotics and Automation,Detroit, MI, USA, 1999, 1240–246.208 doi:10.1109/ROBOT.1999.772531
  22. [22] B. Mirtich & J. Canny, Easily computable optimum grasps in2D and 3D, Proc. IEEE Int. Conf. on Robotics and Automation,San Diego, CA, USA, 1994, 739–747. doi:10.1109/ROBOT.1994.351399
  23. [23] C. Borst, M. Fischer, & G Hirzinger, Calculating hand config-urations for precision and pinch grasps, Proc. IEEE Int. Conf.on Intelligent Robots and Systems, Lausanne, Suisse, 2002,1553–1559. doi:10.1109/IRDS.2002.1043976
  24. [24] Y. Guan & H. Zhang, Kinematic feasibility analysis of 3-D mul-tifingered grasps, IEEE Trans. on Robotics and Automation,19(3), 2003, 507–513. doi:10.1109/TRA.2003.810235
  25. [25] J.A. Coehlo & R.A. Grupen, A control basis for learningmultifingered grasps, Journal of Robotic Systems, 14 (7), 1997,545–557. doi:10.1002/(SICI)1097-4563(199707)14:7<545::AID-ROB3>3.0.CO;2-N
  26. [26] D. Wheeler, A.H. Fagg, & R. Grupen, Learning prospectivepick and place behavior, Proc. IEEE/RSJ Int. Conf. onDevelopment and Learning, Cambridge, MA, USA, 2002, 197–202. doi:10.1109/DEVLRN.2002.1011865
  27. [27] R. Grupen & J. Coelho, Acquiring state form control dynamicsto learn grasping policies for robot hands, International Journalon Advanced Robotics, 16 (5), 2002, 427–444 doi:10.1163/15685530260182927
  28. [28] M. Kuperstein & J. Rubinstein, Implementation of an adap-tative controller for sensory-motor condition, in R. Pfeiffer, Z.Schreter, F. Fogelman-Soulie, & L. Steels (eds.), Connection-ism in perspective (Amsterdam: Elsevier, 1989).
  29. [29] Y. Uno, N. Fukumura, R. Suzuki, & M. Kawato, A computa-tional model for recognizing objects and planning hand shapesin grasping movements, Neural Networks, 8, 1995, 839–851. doi:10.1016/0893-6080(95)00002-H
  30. [30] Z. Taha, R. Brownand, & D. Wright, Modelling and simu-lation of the hand grasping using neural networks, MedicalEngineering and Physiology, 19, 1997, 536–538. doi:10.1016/S1350-4533(97)00019-2
  31. [31] A.H. Fagg & M.A. Arbib, Modeling parietal-premotor interac-tions in primate control of grasping, Neural Networks, 11 (8),1998, 1277–1303. doi:10.1016/S0893-6080(98)00047-1
  32. [32] M.A. Moussa & M.S. Kamel, An experimental approach torobotic grasping using a connectionist architecture and genericgrasping functions, IEEE Trans. on Systems, Man and Cyber-netics, 28, 1998, 239–253. doi:10.1109/5326.669561
  33. [33] J.W. Garret, The adult human hand: Some anthropometricand biomechanical considerations, Human Factors, 13, 1971,117–131.
  34. [34] B. Buchholz, T.J. Armstrong, & S.A. Goldstein, Anthropo-metric data for describing the kinematics of the human hand,Ergonomics, 35, 1992, 261–273. doi:10.1080/00140139208967812
  35. [35] R.S. Sutton & A.G. Barto, Reinforcement learning (Cambridge,MA: MIT Press, 1998).
  36. [36] L.P. Kaelbling, M.L. Littman, & A.W. Moore, Reinforcementlearning: A survey, Journal of Artificial Intelligence Research,4, 1996, 237–285.
  37. [37] R.S. Sutton, Learning to predict by the methods of temporaldifference, Machine Learning, 3, 1988, 9–44.
  38. [38] C.J.C.H. Watkins, Learning from delayed reward, doctoraldiss., Cambridge University, Cambridge, 1989.
  39. [39] R. Munos & A.W. Moore, Variable resolution discretization inoptimal control, Machine Learning, 49, 2002, 291–323. doi:10.1023/A:1017992615625
  40. [40] K. Doya, Reinforcement learning in continuous time and space,Neural Computation, 12, 2000, 243–269. doi:10.1162/089976600300015961
  41. [41] J. Morimoto & K. Doya, Acquisition of stand-up behavior by areal robot using hierarchical reinforcement learning, Roboticsand Autonomous Systems, 36, 2000, 37–51. doi:10.1016/S0921-8890(01)00113-0
  42. [42] J. Campos & F.L. Lewis, Adaptive critic neural network forfeedforward compensation, Proc. American Control Conf., SanDiego, CA, USA, 1999, 2813–2818.
  43. [43] G. Galan & S. Jagannathan, Adaptive critic-based objectcontact controller for a three-fingered gripper, Proc. IEEESymp. on Intelligent Control, Mexico City, Mexico, 2001,109–114. doi:10.1109/ISIC.2001.971493
  44. [44] G. Galan & S. Jagannathan, Adaptive critic-based objectgrasping controller for a three-fingered gripper, Proc. IEEEConf. on Decision and Control, 4, Orlando, FL, USA, 2001,3140–3145. doi:10.1109/CDC.2001.980301
  45. [45] V. Gullapalli, A stochastic reinforcement learning algorithmfor learning real valued functions, Neural Networks, 3, 1990,671–692. doi:10.1016/0893-6080(90)90056-Q
  46. [46] V. Gullapalli, Direct associative reinforcement learning meth-ods for dynamic systems control, Neurocomputing, 9, 1995,271–292. doi:10.1016/0925-2312(95)00035-X
  47. [47] E. Oyama & S. Tachi, Inverse kinematics learning by modulararchitecture neural networks, Proc. IEEE Int. Joint Conf. onNeural Networks, Washington DC, USA, 1999, 2065–2070.
  48. [48] E. Oyama & S. Tachi, Modular neural net system for inversekinematics learning, Proc. IEEE Int. Conf. on Robotics andAutomation, San Francisco, CA, USA, 2000, 3239–3246.

Important Links:

Go Back