• Corpus ID: 1645955

Symbolic level generalization of in-hand manipulation tasks from human demonstrations using tactile

@inproceedings{Martins2010SymbolicLG,
  title={Symbolic level generalization of in-hand manipulation tasks from human demonstrations using tactile},
  author={Ricardo Martins and Diego Resende Faria and J. Dias},
  year={2010}
}
This work intends to contribute to the development of autonomous dexterous robotic hands by presenting an approach to describe the mechanisms underlying the human strategies during the execution of in-hand manipulation tasks. The work proposes a symbolic decription of the inhand manipulation tasks. The in-hand manipulation tasks are demonstrated by a subject wearing an instrumented glove with a tactile sensing array on the palm and fingers region. The description of the manipulation movement… 
ap.isr.uc.pt
9 Citations
Background Citations
3
Methods Citations
4

Figures and Tables from this paper

9 Citations

Citation Type

Citation Type

State-Action Gist based In-hand Manipulation Learning from Human Demonstration
  • G. Cheng
  • Computer Science, Engineering
  • 2013
TLDR
This thesis proposes a human-interactive mechanism to enhance the real robot learning and applies the Gaussian Markov Random Field to extract the action gist from a data-glove.
Sensor prediction and grasp stability evaluation for in-hand manipulation
TLDR
A forward model for the prediction of the touch state resulting from the in-hand manipulation is developed and can accurately predict whether a grasp is stable or whether it results in dropping the object.
Towards an Understanding of Grasping using a Multi-Sensing Approach
TLDR
An everyday manual interaction is investigated, recording hand kinematics, the involved forces and eyemovements, to develop a more complete understanding of what is termed manual intelligence, with a view to enabling robots carry out complex tasks that the authors take for granted.
Probabilistic Classification of Grasping Behaviours Using Visuo-Haptic Perception
TLDR
For a simple set of grasping behaviours defined in this paper, preliminary experimental results indicate that the proposed approach could result in a robust and efficient perception of grasp behaviours.
Versatile In-Hand Manipulation of Objects with Different Sizes and Shapes Using Neural Networks
TLDR
The features extracted by a stacked autoencoder (trained with a larger dataset) could reduce the number of required training samples for supervised learning of in-hand manipulation.
Action gist based automatic segmentation for periodic in-hand manipulation movement learning
TLDR
An algorithm related to the Meta Motion Occurrence Histogram is proposed to maximize the common motions in each segment, so as to figure out the best segmentation solution in the in-hand manipulation sequence.
Robust in-hand manipulation of variously sized and shaped objects
TLDR
This paper uses machine learning to learn in-hand manipulation of such various sized and shaped objects and shows that with deep learning the number of required training sets can be drastically reduced.
Position-force combination control with passive flexibility for versatile in-hand manipulation based on posture interpolation
TLDR
This paper proposes a combined strategy of force control and passive adaptation through soft fingertips with simple interpolation control to achieve in-hand manipulation between various postures and with various objects.
Evaluation of Load Distributions and Contact Areas in 4 Common Grip Types Used in Daily Living Activities.

References

SHOWING 1-9 OF 9 REFERENCES
Coding and use of tactile signals from the fingertips in object manipulation tasks
TLDR
Analysis of signals in tactile afferent neurons and central processes in humans reveals how contact events are encoded and used to monitor and update task performance.
Recognition of in-hand manipulation using contact state transition for multifingered robot hand control
A sensor fusion approach for recognizing continuous human grasping sequences using hidden Markov models
TLDR
A system is presented that uses both hand shape and contact-point information obtained from a data glove and tactile sensors to recognize continuous human-grasp sequences and is made by a hidden Markov model recognizer.
On Learning, Representing, and Generalizing a Task in a Humanoid Robot
We present a programming-by-demonstration framework for generically extracting the relevant features of a given task and for addressing the problem of generalizing the acquired knowledge to different…
Robot programming by human demonstration: adaptation and inconsistency in constrained motion
  • N. Delson, H. West
  • Computer Science
    Proceedings of IEEE International Conference on Robotics and Automation
  • 1996
TLDR
This article presents an approach for identifying a range of acceptable robot force and motion trajectories from multiple human demonstrations and applies this approach to simple assembly tasks consisting of 3D translation.
Learning Actions from Observations
TLDR
This article proposes an unsupervised learning approach for action primitives that make use of the human movements as well as object state changes, and proposes using parametric hidden Markov models (PHMMs) for representing the discoveredaction primitives.
Development of hand skills in the child
D euelopment ofHand Skills in the Child is a refl-eshingly concise, yet complete, soft-bound reference for the peel iatric occupational therapy rractitionel-. It has no peer for current occurational…
Hidden Markov model for intelligent extraction of robot trajectory command from demonstrated trajectories
  • S. Tso, K. Liu
  • Computer Science
    Proceedings of the IEEE International Conference on Industrial Technology (ICIT'96)
  • 1996
TLDR
A scheme for selecting the best robot trajectory from a number of demonstrated trajectories based on the hidden Markov model (HMM) technique and is divided into four stages, which reflects the consistency of the trajectory with the HMM.
/www.tekscan.com/industrial/grip-system.html
  • IEEE/RSJ International Conference on Intelligent Robots and Systems Workshop on Grasp Planning and Task Learning by Imitation
  • 2010