Dexterous Skills Transfer by Extending Human Body Schema to a Robotic Hand

Öztop, Erhan; Lin, Liheng; Kawato, Mitsuo; Cheng, Gordon

doi:10.1109/ichr.2006.321367

Cited by 24 publications

(18 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…After the training period, people typically adapt themselves well to the kinematical and dynamical properties of various devices without conscious effort and are able to naturally absorb the relationship between their own body and the dynamics of the tool or device they are using. These properties have been recently highlighted by [8], [9], and are well supported by the neurophysiological experiments where researchers show that primates have very plastic demonstrations of limbs, which are expanded immediately upon acquisition of tools [10], [11]. Similarly, human perception of body shape and orientation is adaptable within a period of seconds [12].…”

Section: Introductionmentioning

confidence: 81%

Utilization of human sensorimotor learning capacity for obtaining novel robot behaviours: 2-DOF ball balancing on a parallel platform

Babič

2011

2011 IEEE International Conference on Robotics and Biomimetics

View full text Add to dashboard Cite

We propose a novel method for acquiring robot skill synthesis that exploits human capability to learn and to control complex tools and devices. The basic idea is to consider the target robotic system as a complex tool akin a computer mouse or a car that can be intuitively controlled by a human. Once the human learns how to control the robotic system effortlessly, the target behaviour can be obtained by the human on the robot through practice. The successful execution of the desired task by the human via the robot implies that the required control commands have been discovered by the human, and can subsequently be used for designing controller that operate autonomously. In this article, we demonstrate this idea by presenting a 2-DOF ball balancing task on a parallel platform obtained with the proposed method.

show abstract

Section: Introductionmentioning

confidence: 81%

Utilization of human sensorimotor learning capacity for obtaining novel robot behaviours: 2-DOF ball balancing on a parallel platform

Babič

2011

2011 IEEE International Conference on Robotics and Biomimetics

View full text Add to dashboard Cite

show abstract

“…Many types of disturbances were tolerated and self-corrected with this open-loop controller obtained through human dexterity. Moreover, although we have not used different balls during human performance, the controller was able to swap balls with different sizes and weights, such as a wooden and coated metal ball; a coated but larger metal ball, and finally a large but very light Styrofoam ball [12] .…”

Section: B Ball Swapping Task Performancementioning

confidence: 99%

“…If we can achieve our goal then the second stage will be to develop algorithms for deriving autonomous controllers for the tasks controlled by human (motor) intelligence. In an earlier report, we have presented the preliminary results of this stage, where the robot could swap balls very slowly (7.5 seconds/swap) [12].…”

Section: Introductionmentioning

confidence: 98%

Extensive Human Training for Robot Skill Synthesis: Validation on a Robotic Hand

Öztop¹,

Lin²,

Kawato³

et al. 2007

Proceedings 2007 IEEE International Conference on Robotics and Automation

Self Cite

View full text Add to dashboard Cite

We propose a framework for skill synthesis for robots that exploits the human capacity to learn novel control tasks. The conceptual idea is to incorporate the target robotic platform into the experimenter's body schema so that it can be controlled effortlessly as if the robot were a part of the body. Once this stage is achieved, the dexterity on a task exhibited with the new external limb -the robot-can be used for designing controllers for the task under consideration. This article exemplifies the proposed framework by showing the derivation of an effective open-loop controller that can manipulate two balls with the fingers of a 16-DOF robotic hand.

show abstract

“…Using this indirect method that follows the 'Robot Skill Synthesis via Human Learning' paradigm [25], we recorded sequences of hand postures during cap turning movements for five different cap radii (r = 1.5cm to 3.5cm). For each of these radii, we produced five sequences each of about 30 to 45 hand postures.…”

Section: Extracting a Manipulation Manifold From Human Training Datamentioning

confidence: 99%

Bio-inspired motion strategies for a bimanual manipulation task

Steffen

Elbrechter

Haschke

et al. 2010

2010 10th IEEE-RAS International Conference on Humanoid Robots

View full text Add to dashboard Cite

Abstract-We consider the complex task of coordinating two five-fingered anthropomorphic robot hands for taking a jar passed from a human user and unscrewing its cap. Using a pair of 7-DOF redundant arms for operating the hands, we study how the incorporation of human movement strategies at the finger and arm levels can aid in the solution of the overall bimanual task. At the finger level, we employ a finger control manifold for the unscrewing motion that has been synthesized with a kernel approach applied to human motion data captured with a data glove. At the arm level, we use a heuristic motivated from the observation of human arm movements to enhance the space of pass-over configurations that the system can successfully handle. In addition, we provide a brief description of the architecture of the overall system that comprises 54 motor degrees of freedom and integrates camera vision, arm and finger control as well as a speech output component for interaction with the human user.

show abstract

Dexterous Skills Transfer by Extending Human Body Schema to a Robotic Hand

Cited by 24 publications

References 13 publications

Utilization of human sensorimotor learning capacity for obtaining novel robot behaviours: 2-DOF ball balancing on a parallel platform

Utilization of human sensorimotor learning capacity for obtaining novel robot behaviours: 2-DOF ball balancing on a parallel platform

Extensive Human Training for Robot Skill Synthesis: Validation on a Robotic Hand

Bio-inspired motion strategies for a bimanual manipulation task

Contact Info

Product

Resources

About