Advertisement

Neural Network Models for Reaching and Dexterous Manipulation in Humans and Anthropomorphic Robotic Systems

  • Rodolphe J. Gentili
  • Hyuk Oh
  • Javier Molina
  • José L. Contreras-Vidal
Chapter
Part of the Springer Series in Cognitive and Neural Systems book series (SSCNS)

Abstract

One fundamental problem for the developing brain as well as for any artificial system aiming to control a complex kinematic mechanism, such as a redundant anthropomorphic limb or finger, is to learn internal models of sensorimotor transformations for reaching and grasping. This is a complex problem since the mapping between sensory and motor spaces is generally highly nonlinear and depends of the constraints imposed by the changing physical attributes of the limb and hand and the changes in the developing brain. Previous computational models suggested that the development of visuomotor behavior requires a certain amount of simultaneous exposure to patterned proprioceptive and visual stimulation under conditions of self-produced movement—referred to as ‘motor babbling.’ However, the anthropomorphic geometrical constraints specific to the human arm and finger have not been incorporated in these models for performance in 3D. Here we propose a large scale neural network model composed of two modular components. The first module learns multiple internal inverse models of the kinematic features of an anthropomorphic arm and fingers having seven and four degree of freedom, respectively. Once the 3D inverse kinematics of the limb/finger are learned, the second module learns a simplified control strategy for the whole hand shaping during grasping tasks that provides a realistic coordination among fingers. These two bio-inspired neural models functionally mimic specific cortical features and are able to reproduce reaching and grasping human movements. The high modularity of this neural model makes it well suited as a high-level neuro-controller for planning and control of grasp motions in actual anthropomorphic robotic system.

Keywords

Hide Layer Neural Network Model Motor Command Inverse Kinematic Neural Model 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Notes

Acknowledgments

This work was supported in part by the Office of Naval Research (N000140910126) and the National Institutes of Health (PO1HD064653). Rodolphe J. Gentili would like to sincerely thank La Fondation Motrice, Paris, France, for the continued support of his research.

References

  1. .
    Abend W, Bizzi E, Morasso P. (1982). Human arm trajectory formation. Brain, 705:331–348CrossRefGoogle Scholar
  2. .
    Albus JS. (1971). A theory of cerebellar function. Math. Biosci., 10:25–61CrossRefGoogle Scholar
  3. .
    Atkeson CG, Hollerbach JM. (1985). Kinematic features of unrestrained vertical arm movements. J. Neurosci., 5(9):2318–2330PubMedGoogle Scholar
  4. .
    Baraduc P, Guigon E, Burnod Y. (2001). Recoding arm position to learn visuomotor transformations. Cereb. Cortex, 11(10):906–917CrossRefPubMedGoogle Scholar
  5. .
    Baraduc P, Guigon E. (2002). Population computation of vectorial transformations. Neural Comput., 14(4):845–871CrossRefPubMedGoogle Scholar
  6. .
    Braido P, Zhang X. (2004). Quantitative analysis of finger motion coordination in hand manipulative and gestic acts. Hum. Mov. Sci., 22:661–678CrossRefPubMedGoogle Scholar
  7. .
    Bullock D, Grossberg S. (1988). Neural dynamics of planned arm movements: emergent invariants and speed-accuracy trade-offs during trajectory formation. Psychol. Rev., 95(1):49–90CrossRefPubMedGoogle Scholar
  8. .
    Bullock D, Grossberg S, Guenther FH. (1993). A self organizing neural model for motor equivalent reaching and tool use by a multijoint arm. J. Cogn. Neurosci., 5(4):408–435CrossRefGoogle Scholar
  9. .
    Bullock D, Cisek P, Grossberg S. (1998). Cortical networks for control of voluntary arm movements under variable force conditions. Cereb. Cortex, 8(1):48–62CrossRefPubMedGoogle Scholar
  10. .
    Burnod Y, Baraduc P, Battaglia-Mayer A, Guigon E, Koechlin E, Ferraina S, Lacquaniti F, Caminiti R. (1999). Parieto-frontal coding of reaching: an integrated framework. Exp. Brain Res., 129:325–346CrossRefPubMedGoogle Scholar
  11. .
    Caminiti R, Johnson PB, Urbano A. (1990). Making arm movements within different parts of space: dynamic aspects in the primate motor cortex. J Neurosci., 10:2039–2058PubMedGoogle Scholar
  12. .
    Caminiti R, Ferraina S, Johnson PB. (1996). The sources of visual input to the primate frontal lobe: a novel role for the superior parietal lobule. Cereb. Cortex, 6:102–119CrossRefPubMedGoogle Scholar
  13. .
    Cohen YE, Andersen R. (2002). A common reference frame for movement plans in posterior parietal cortex. Nat. Rev. Neurosci., 3:553–562CrossRefPubMedGoogle Scholar
  14. .
    Conforto S, Bernabucci I, Severini G, Schmid M, D’Alessio T. (2009). Biologically inspired modelling for the control of upper limb movements: from concept studies to future applications. Front. Neurorobotics, 3(3):1–5Google Scholar
  15. .
    Contreras-Vidal JL, Grossberg S, Bullock D. (1997). A neural model of cerebellar learning for arm movement control: cortico-spino-cerebellar dynamics. Learn. Mem., 3(6):475–502CrossRefPubMedGoogle Scholar
  16. .
    Contreras-Vidal JL, Bo J, Boudreau JP, Clark JE. (2005). Development of visuomotor representations for hand movement in young children. Exp. Brain Res., 162(2):155–164CrossRefPubMedGoogle Scholar
  17. .
    Contreras-Vidal JL. (2006). Development of forward models for hand localization and movement control in 6- to 10-year-old children. Hum. Mov. Sci., 25(4–5):634–645CrossRefPubMedGoogle Scholar
  18. .
    Cutkosky MR. (1989). On grasp choice, grasp models and the design of hands for manufacturing tasks. IEEE Trans. Rob. Autom., 5(3):269–279CrossRefGoogle Scholar
  19. .
    Cutkosky MR, Howe RD. (1990). Human grasp choice and robotic grasp analysis. In ST Venkataraman and T Iberall (Eds), Dextrous robot hands. New York: Springer, pp. 5–31Google Scholar
  20. .
    Desmurget M, Epstein CM, Turner RS, Prablanc C, Alexander GE, Grafton ST. (1999). Role of the posterior parietal cortex in updating reaching movements to a visual target. Nat. Neurosci., 2(6):563–567CrossRefPubMedGoogle Scholar
  21. .
    Doya K. (1999). What are the computations of cerebellum, the basal ganglia, and the cerebral cortex? Neural Netw., 12:961–974CrossRefPubMedGoogle Scholar
  22. .
    Fagg AH, Arbib MA. (1998). Modeling parietal-premotor interactions in primate control of grasping. Neural Netw., 11(7–8):1277–1303CrossRefPubMedGoogle Scholar
  23. .
    Ferraina S, Garasto MR, Battaglia-Mayer A, Ferraresi P, Johnson PB, Lacquaniti F, Caminiti R. (1997a). Visual control of hand-reaching movement: activity in parietal area7m. Eur. J. Neurosci., 9:1090–1095CrossRefPubMedGoogle Scholar
  24. .
    Ferraina S, Johnson PB, Garasto MR, Battaglia-Mayer A, Ercolani L, Bianchi L, Lacquaniti F, Caminiti R. (1997b). Combination of hand and gaze signals during reaching: activity in parietal area 7m of the monkey. J. Neurophysiol., 77:1034–1038PubMedGoogle Scholar
  25. .
    Fiala JC. (1994). A network for learning kinematics with application to human reaching models. Proc. IEEE Int. Conf. Neural Netw., 5:2759–2764Google Scholar
  26. .
    Flash T, Hogan N. (1985). The coordination of arm movements: an experimentally confirmed mathematical model. J. Neurosci., 5(7):1688–1703PubMedGoogle Scholar
  27. .
    Fogassi L, Gallese V, Buccino G, Craghiero L, Fadiga L, Rizzolatti G. (2001). Cortical mechanism for the visual guidance of hand grasping movements in the monkey: a reversible inactivation study. Brain, 124:571–586CrossRefPubMedGoogle Scholar
  28. .
    Gallese V, Fadiga L, Fogassi L, Luppino G, Murata A. (1997). A parietal-frontal circuit for hand grasping movements in the monkey: evidence from reversible inactivation experiments. In P Thier and HO Karnath (Eds), Parietal lobe contributions to orientation in 3D space. Berlin: Springer, pp. 255–270Google Scholar
  29. .
    Gan JQ, Oyama E, Rosales EM, Hu H. (2005). A complete analytical solution to the inverse kinematics of the pioneer 2 robotic arm. Robotica, 23(1):123–129CrossRefGoogle Scholar
  30. .
    Gentili RJ, Papaxanthis C, Ebadzadeh M, Ouanezar S, Eskiizmirliler S, Darlot C, Maier M. (2006). Internal representation of gravitational forces in cerebellar pathways allows for the dynamic inverse computation of vertical pointing movements of a robot arm. Program No. 57.7. 2006 Neuroscience Meeting Planner. Atlanta, GA: Society for Neuroscience, 2006. Online.Google Scholar
  31. .
    Gentili R, Papaxanthis C, Ebadzadeh M, Ouanezar S, Eskiizmirliler S, Darlot C, Maier MA. (2007). Sensorimotor predictions in cerebellar pathways allows inverse dynamic computation of the gravitational forces on vertical pointing movement of a robot arm. NEASB Conference, University of Maryland, College Park, USAGoogle Scholar
  32. .
    Gentili RJ, Contreras-Vidal JL. (2008). A neural model of cortico-spino-cerebellar learning for force computation during precision grip. Program No. 77.9/NN31. 2008 Neuroscience Meeting Planner. Washington, DC: Society for Neuroscience, 2008. OnlineGoogle Scholar
  33. .
    Gentili RJ, Charalambos P, Ebadzadeh M, Eskiizmirliler S, Ouanezar S, Darlot C. (2009a). Integration of gravitational torques in cerebellar pathways allows for the dynamic inverse computation of vertical pointing movements of a robot arm. PLoS One, 4(4):e5176CrossRefPubMedGoogle Scholar
  34. .
    Gentili RJ, Oh H, Contreras-Vidal JL. (2009b) A cortical neural model for inverse kinematics computation of an anthropomorphic robot finger. Program No. 862.15. 2009 Neuroscience Meeting Planner. Chicago, IL: Society for Neuroscience, 2009. Online.Google Scholar
  35. .
    Georgopoulos AP, Kalaska JF, Curtcher MD, Caminiti R, Massey JT. (1984). The representation of movement direction in the motor cortex: single cell and population studies. In GM Edelman, WE Gall and WM Cowan (Eds), Dynamic aspects of cortical function. New York: Wiley, pp. 501–524Google Scholar
  36. .
    Georgopoulos AP, Schwartz AN, Kettner RE. (1986). Neuronal population coding of movement direction. Science, 233:1416–1419CrossRefPubMedGoogle Scholar
  37. .
    Ghez C, Gordon J, Ghilardi MF, Sainburg R. (1994). Contributions of vision and perception to accuracy in limb movements. In MS Gazzaniga (Eds), The cognitive neurosciences. Cambridge: MIT, pp. 549–564Google Scholar
  38. .
    Goodale MS, Milner AD. (1992). Separate visual pathways for perception and action. Trends Neurosci., 15:20–25CrossRefPubMedGoogle Scholar
  39. .
    Gorce P, Fontaine JG. (1996). Design methodology for flexible grippers. J. Intell. Robot. Syst., 15(3):307–328CrossRefGoogle Scholar
  40. .
    Gordon J, Ghiraldi MF, Ghez C. (1994). Accuracy of planar reaching movements. I. independence of direction and extent variability, Exp. Brain Res., 99:97–111Google Scholar
  41. .
    Grinyagin IV, Biryukova EV, Maier MA. (2005). Kinematic and dynamic synergies of human precision-grip movements. J. Neurophysiol., 94(4):2284–2294CrossRefPubMedGoogle Scholar
  42. .
    Grosse-Wentrup M, Contreras-Vidal JL. (2007). The role of the striatum in adaptation learning: a computational model. Biol. Cybern., 96(4):377–388CrossRefPubMedGoogle Scholar
  43. .
    Guenther FH, Micci-Barreca D. (1997). Neural models for flexible control of redundant systems. In PG Morasso and V Sanguinetti (Eds), Self-organization, computational maps and motor control. North-Holland Psychology series, Elsevier, pp. 383–421CrossRefGoogle Scholar
  44. .
    Guigon E, Grandguillaume P, Otto I, Boutkhil L, Burnod Y. (1994). Neural network models of cortical functions based on the computational properties of the cerebral cortex. J. Physiol., 88:291–308Google Scholar
  45. .
    HartenBerg RS, Denavit J. (1964). Kinematic synthesis of linkages. McGraw-Hill, New YorkGoogle Scholar
  46. .
    Hollerbach JM, Moore SP, Atkeson CG. (1986). Workspace effect in arm movement kinematics derived by joint interpolation. In G Ganchev, B Dimitrov and P Patev (Eds), Motor control. New York: Plenum, pp. 197–208Google Scholar
  47. .
    Hulliger M. (1984). The mammalian muscle spindle and its central control. Rev. Physiol. Biochem. Pharmacol., 101:1–110CrossRefPubMedGoogle Scholar
  48. .
    Iberall T. (1987). Grasp planning for human prehension. Proceedings of the 10 th International Conference on Artificial Intelligence, Milan, Italy, pp. 1153–1156Google Scholar
  49. .
    Iberall T, Jackson J, Labbe L, Zamprano R. (1988). Knowledge based prehension: capturing human dexterity. Proceedings of the IEEE International Conference on Robotics and Automation, Philadelphia, PA, USA, pp. 82–87Google Scholar
  50. .
    Iberall T. (1997). Human prehension and dexterous robot hands. Int. J. Rob. Res., 16(3):285–299CrossRefGoogle Scholar
  51. .
    Ito M. (1984). The cerebellum and neural control. Raven, New YorkGoogle Scholar
  52. .
    Jeannerod M. (1991). The interaction of visual and proprioceptive cues in controlling reaching movements. In DR Humphrey and HJ Freund (Eds), Motor control: concepts and issues. New York: Wiley, pp. 277–291Google Scholar
  53. .
    Jeannerod M. (1994). The hand and the object: the role of posterior parietal cortex in forming motor representations. Can. J. Physiol. Pharmacol., 72:535–541PubMedGoogle Scholar
  54. .
    Johnson PB, Ferraina S, Garasto MR, Battaglia-Mayer A, Ercolani L, Burnod Y, Caminiti R. (1997). From vision to movement: cortico-cortical connections and combinatorial properties of reaching related neurons in parietal areas V6 and V6A. In P Their and O Karnath (Eds), Parietal lobe contributions to orientation in 3D space. Heidelberg: Springer, pp. 221–236Google Scholar
  55. .
    Jordan MI, Rumelhart DE. (1992). Forward models: supervised learning with a distal teacher. Cogn. Sci., 16:307–354CrossRefGoogle Scholar
  56. .
    Kalaska JF, Cohen DAD, Prud’homme M, Hyde ML. (1990). Parietal area 5 neuronal activity encodes movement kinematics, not movement dynamics. Exp. Brain Res., 80:351–364CrossRefPubMedGoogle Scholar
  57. .
    Kang SB, Ikeuchi K. (1997). Toward automatic robot instruction from perception: mapping human grasps to manipulator grasps. IEEE Trans. Rob. Autom., 13(1):81–95CrossRefGoogle Scholar
  58. .
    Kerr J, Roth R. (1986). Analysis of multifingered hands. Int. J. Rob. Res., 4:3–17CrossRefGoogle Scholar
  59. .
    Kuperstein M. (1991). Infant neural controller for adaptive sensory-motor coordination. Neural Netw., 4(2):131–146CrossRefGoogle Scholar
  60. .
    Luppino G, Murata A, Govoni P, Matelli M. (1999). Largely segregated parietofrontal connections linking rostral intraparietal cortex (areas AIP and VIP) and ventral premotor cortex (areas F5 and F4). Exp. Brain Res., 128:181–187CrossRefPubMedGoogle Scholar
  61. .
    Marr D. (1969). A theory of cerebellar cortex. J. Physiol., 202:437–470PubMedGoogle Scholar
  62. .
    Mason CR, Gomez JE, Ebner TJ. (2001). Hand synergies during reach-to-grasp. J. Neurophysiol., 86(6):2896–2910PubMedGoogle Scholar
  63. .
    Molina-Vilaplana J, Pedreno-Molina JL, Lopez-Coronado J. (2004). Hyper RBF model for accurate reaching in redundant robotic systems. Neurocomputing, 61:495–501CrossRefGoogle Scholar
  64. .
    Molina-Vilaplana J, López-Coronado J. (2006). A neural network model for coordination of hand gesture during reach to grasp. Neural Netw., 19:12–30CrossRefGoogle Scholar
  65. .
    Molina-Vilaplana J, Feliu-Batlle J, Lopez-Coronado J. (2007). A modular neural network architecture for step-wise learning of grasping tasks. Neural Netw., 20(5):631–645CrossRefPubMedGoogle Scholar
  66. .
    Molina-Vilaplana J, Contreras-Vidal JL, Herrero-Ezquerro MT, López Coronado J. (2009). A model for altered neural network dynamics related to prehension movements in parkinson disease. Biol. Cybern., 100(4):271–287CrossRefPubMedGoogle Scholar
  67. .
    Morasso P. (1981). Spatial control of arm movements. Exp. Brain Res., 42(2):223–227CrossRefPubMedGoogle Scholar
  68. .
    Moussa MA, Kamel MS. (1998). An experimental approach to robotic grasping using a connectionist architecture and generic grasping functions. IEEE Trans. Syst. Man Cybern. C Appl Rev., 28(2):239–253CrossRefGoogle Scholar
  69. .
    Murata A, Gallese V, Kaseda K, Sakata H. (1996). Parietal neurons related to memory guided hand manipulation. J. Neurophysiol., 75:2180–2186PubMedGoogle Scholar
  70. .
    Murata A, Fadiga L, Fogassi L, Gallese V, Raos V, Rizzolatti G. (1997). Object representations in the ventral premotor cortex of the monkey. J. Neurophysiol., 78:2226–2230PubMedGoogle Scholar
  71. .
    Murata A, Gallese V, Luppino G, Kaseda K, Sakata H. (2000). Selectivity for the shape, size and orientation of objects for grasping in neurons of monkey parietal area AIP. J. Neurophysiol., 83:339–365Google Scholar
  72. .
    Morrey BF, Chao EY. (1976). Passive motion of the elbow joint. J. Bone Joint Surg. Am., 58:501–508PubMedGoogle Scholar
  73. .
    Napier JR. (1956). The prehensile movements of the human hand. J. Bone Joint Surg., 38B:902–913Google Scholar
  74. .
    Pause M, Kunesch E, Binkofski F, Freund HJ. (1989). Sensorimotor disturbances in patients with lesions in parietal cortex. Brain, 112:1599–1625CrossRefPubMedGoogle Scholar
  75. .
    Pedreño-Molina JL, Molina-Vilaplana J, López-Coronado J, Gorce P. (2005). A modular neural network linking hyper RBF and AVITE models for reaching moving objects. Robotica, 23:625–633CrossRefGoogle Scholar
  76. .
    Poggio T, Girosi F. (1989). A theory of networks for approximation and learning. AI Memo 1140, MITGoogle Scholar
  77. .
    Pons JL, Ceres R, Pfeiffer F. (1999). Multifingered dextrous robotic hands design and control: a review. Robotica, 17(6):661–674CrossRefGoogle Scholar
  78. .
    Porter R, Lemon RN. (1993). Corticospinal function and voluntary movement. Oxford University Press, New YorkGoogle Scholar
  79. .
    Pouget A, Snyder LH. (2000). Computational approaches to sensorimotor transformations. Nature, 3:1192–1198Google Scholar
  80. .
    Rizzolatti G, Camarda R, Fogassi L, Gentilucci M, Luppino G, Matelli M. (1988). Functional organization of inferior area 6 in the macaque monkey.II.area F5 and the control of distal movement. Exp. Brain Res., 71:491–507Google Scholar
  81. .
    Rizzolatti G, Gentilucci M, Camarda R, Gallese V, Luppino G, Matelli M, Fogassi R. (1990). Neurons related to reaching-grasping arm movements in the rostral part of area 6 (area 6 beta). Exp. Brain Res., 82:337–350CrossRefPubMedGoogle Scholar
  82. .
    Sakata H, Taira M, Murata A, Mine S. (1995). Neural mechanisms of visual guidance of hand action in the parietal cortex of the monkey. Cereb. Cortex, 5:429–438CrossRefPubMedGoogle Scholar
  83. .
    Santello M, Flanders M, Soechting JF. (2002). Patterns of hand motion during grasping and the influence of sensory guidance. J. Neurosci., 22(4):1426–1435PubMedGoogle Scholar
  84. .
    Shadmehr R, Wise SP. (2005). Computational neurobiology of reaching and pointing: a foundation for motor learning. MIT, Cambridge MAGoogle Scholar
  85. .
    Sheng L, Yiqing W, Qingwei Ch, Weili H. (2006). A new geometrical method for the inverse kinematics of the hyper-redundant manipulators. IEEE Int. Conf. Robot. Biomim., pp. 1356–1359Google Scholar
  86. .
    Snyder LH, Batista AP, Andersen RA. (1997). Coding of intention in the posterior parietal cortex. Nature, 386:167–170CrossRefPubMedGoogle Scholar
  87. .
    Swett BA, Contreras-Vidal JL, Birn R, Braun AR. (2010). Neural substrates of graphomotor sequence learning: A combined fMRI and kinematic study. J Neurophysiol., 103(6):3366–3377CrossRefPubMedGoogle Scholar
  88. .
    Taha Z, Brown R, Wright D. (1997). Modeling and simulation of the hand grasping using neural networks. Med. Eng. Physiol., 19(6):536–538CrossRefGoogle Scholar
  89. .
    Tikhonov AN, Arsenin VY. (1977). Solutions of ill-posed problems. WH Winston (Ed). Washington DCGoogle Scholar
  90. .
    Todorov E, Jordan MI. (2002). Optimal feedback control as a theory of motor coordination. Nat. Neurosci., 5(11):1226–1235CrossRefPubMedGoogle Scholar
  91. .
    Todorov E. (2004). Optimality principles in sensorimotor control. Nat. Neurosci., 7(9):907–915CrossRefPubMedGoogle Scholar
  92. .
    Ulloa A, Bullock D. (2003). A neural network simulating human reach-grasp coordination by updating of vector positioning commands. Neural Netw., 16:1141–1160CrossRefPubMedGoogle Scholar
  93. .
    Ungerleider LG, Mishkin M. (1982) Two cortical visual systems. In DJ Ingle, MA Goodale and RJW Mansfield (Eds), Analysis of visual behavior. Cambridge, MA: MIT, pp. 549–586Google Scholar
  94. .
    Uno Y, Kawato M, Suzuki R. (1989). Formation and control of optimal trajectory in human multijoint arm movement. Minimum torque-change model. Biol. Cybern., 61(2):89–101Google Scholar
  95. .
    Uno Y, Fukumura N, Suzuki R, Kawato M. (1995). A computational model for recognizing objects and planning hand shapes in grasping movements. Neural Netw., 8(6):839–851CrossRefGoogle Scholar
  96. .
    Wimmers RH, Savelsbergh GJ, Peek PJ, Hopkins B. (1998). Evidence for a phase transition in the early development of prehension. Dev. Psychobiol., 32:235–248CrossRefPubMedGoogle Scholar
  97. .
    Wise SP, Boussaoud D, Johnson PB, Caminiti R. (1997). Premotor and parietal cortex: cortico-cortical connectivity and combinatorial computations. Annu. Rev. Neurosci., 20:25–42CrossRefPubMedGoogle Scholar
  98. .
    Woelfl K, Pfeiffer F. (1995). Grasp strategies for a dextrous robotic hand. In V Graefe (Ed), Intelligent robots and systems. Amsterdam: Elsevier, pp. 259–277Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2011

Authors and Affiliations

  • Rodolphe J. Gentili
  • Hyuk Oh
  • Javier Molina
  • José L. Contreras-Vidal
    • 1
    • 2
    • 3
  1. 1.School of Public Health, Department of KinesiologyUniversity of MarylandCollege ParkUSA
  2. 2.Graduate Program in Neuroscience and Cognitive Science (NACS)University of MarylandCollege ParkUSA
  3. 3.Graduate Program in BioengineeringUniversity of Maryland, School of Public HealthCollege ParkUSA

Personalised recommendations