Repetitive grasping with anthropomorphic skin-covered hand enables robust haptic recognition

Skin is an essential component of artificial hands. It enables the use of object affordance for recognition and control, but due to its intrinsic locality and low density of current tactile sensors, stable and proper manual contacts with the objects are indispensable. Recently, design of hand structure have shown to be effective for adaptive grasping. However, such adaptive design are only introduced to the fingers in existing works of haptics and their role in recognition remains unclear. This paper introduces the design of the Bionic Hand; an anthropomorphic hand with adaptive design introduced to the whole hand and fully covered with sensitive skin. The experiment shows that anthropomorphic design of hand structure enables robust haptic recognition by convergence of object contact conditions into stable representative states through repetitive grasping. The structure of the human hand is found to solve the issue of narrowing down the sensor space for haptic object recognition by morphological computation.

[1]  Koh Hosoda,et al.  Acquisition of Multi-Modal Expression of Slip through Pick-Up Experiences , 2006, IROS.

[2]  E. Bushnell,et al.  Motor development and the mind: the potential role of motor abilities as a determinant of aspects of perceptual development. , 1993, Child development.

[3]  Esa Alhoniemi,et al.  Clustering of the self-organizing map , 2000, IEEE Trans. Neural Networks Learn. Syst..

[4]  Gianluca Palli,et al.  Development of UB Hand 3: Early Results , 2005, Proceedings of the 2005 IEEE International Conference on Robotics and Automation.

[5]  G. Lundborg,et al.  Sensory substitution in prosthetics. , 2001, Hand clinics.

[6]  Wenwei Yu,et al.  Mutual Adaptation in a Prosthetics Application , 2003, Embodied Artificial Intelligence.

[7]  Yoji Umetani,et al.  The Development of Soft Gripper for the Versatile Robot Hand , 1978 .

[8]  L. Natale,et al.  Learning haptic representation of objects , 2004 .

[9]  Silvestro Micera,et al.  Design of a cybernetic hand for perception and action , 2006, Biological Cybernetics.

[10]  K. Watanabe,et al.  A multi-link robotic finger-type soft touch-sensor system , 2004, Proceedings of IEEE Sensors, 2004..

[11]  Rolf Pfeifer,et al.  Understanding intelligence , 2020, Inequality by Design.

[12]  Minoru Asada,et al.  Anthropomorphic robotic soft fingertip with randomly distributed receptors , 2006, Robotics Auton. Syst..

[13]  A.M. Dollar,et al.  A robust compliant grasper via shape deposition manufacturing , 2006, IEEE/ASME Transactions on Mechatronics.

[14]  H. Ralston,et al.  The pattern of cutaneous innervation of the human foot. , 1958, The American journal of anatomy.

[15]  Pattie Maes,et al.  Toward the Evolution of Dynamical Neural Networks for Minimally Cognitive Behavior , 1996 .

[16]  Design of a Dextrous Hand for advanced CLAWAR applications , 2003 .

[17]  Robert D. Howe,et al.  Towards grasping in unstructured environments: grasper compliance and configuration optimization , 2005, Adv. Robotics.

[18]  John M. Hollerbach,et al.  An integrated tactile and thermal sensor , 1986, Proceedings. 1986 IEEE International Conference on Robotics and Automation.

[19]  Henry J. Ralston,et al.  The pattern of cutaneous innervation of the human hand. , 1958, The American journal of anatomy.

[20]  R. Pfeifer,et al.  Morphological computation for adaptive behavior and cognition , 2006 .

[21]  Jorma Laaksonen,et al.  SOM_PAK: The Self-Organizing Map Program Package , 1996 .

[22]  Yasuo Kuniyoshi,et al.  Haptic Detection of Object affordances by a Multi-fingered Robot Hand , 2005, Int. J. Humanoid Robotics.

[23]  Andrew A. Goldenberg,et al.  Soft Robotic Fingertips , 1996 .

[24]  S. Takamuku,et al.  Haptic discrimination of material properties by a robotic hand , 2007, 2007 IEEE 6th International Conference on Development and Learning.

[25]  Reinhard Wolf,et al.  Visual pattern recognition in Drosophila involves retinotopic matching , 1993, Nature.