Extracting data from human manipulation of objects towards improving autonomous robotic grasping

@article{Faria2012ExtractingDF,
  title={Extracting data from human manipulation of objects towards improving autonomous robotic grasping},
  author={Diego Resende Faria and Ricardo Martins and Jorge Lobo and J. Dias},
  journal={Robotics Auton. Syst.},
  year={2012},
  volume={60},
  pages={396-410}
}
Knowledge-based reasoning from human grasp demonstrations for robot grasp synthesis
Recording hand-surface usage in grasp demonstrations
TLDR
This work proposes a data glove covered with tactile sensors in order to obtain tactile and configuration information simultaneously and uses a kinematic model of the hand, accounting for pronation/supination of the thumb, and scaled according to the hand measurements of the demonstrator, to reconstruct the geometry of the grasping surfaces.
Towards comprehensive capture of human grasping and manipulation skills
TLDR
A new setup for a “sensorized” data glove is proposed to address limitations and through which a more complete picture of human hand response in grasping and manipulation can be obtained.
Leveraging distributed contact force measurements for slip detection: a physics-based approach enabled by a data-driven tactile sensor
TLDR
A novel model-based slip detection pipeline that can predict possibly failing grasps in real-time and signal a necessary increase in grip force and exploits physics to generalize across different tasks is described.
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.
Multiple Sensors Based Hand Motion Recognition Using Adaptive Directed Acyclic Graph
TLDR
A novel and effective multiple sensor based hand motion capture and recognition system that contains abundant information from multimodal human hand motions with the multiple sensor techniques, and it is potentially applicable to applications in prosthetic hand control and artificial systems performing autonomous dexterous manipulation.
A data-driven statistical framework for post-grasp manipulation
TLDR
A general statistical framework is presented to address the problems of grasping an object, and its effectiveness experimentally in placing, dropping, and insertion tasks is demonstrated.
Extracting grasping, contact points and objects motion from assembly demonstration
TLDR
This framework aims at capturing the necessary data to reproduce the assembly motion on a dual-arm robot for future work.
A compact representation of human single-object grasping
TLDR
This work presents hypothesis-driven experiments that emphasize the centrality of environmental constraints in human grasping and extracts from data a simple “grasping plan” that is a generative model for all of the human grasping trials the authors observed.
Learning Task-Oriented Grasp Heuristics from Demonstration by Reymundo
TLDR
Overall, this work demonstrates that the inclusion of unsupervised motion clustering techniques into a grasp learning pipeline can assist in the production of task-oriented models without the typical overhead of direct task constraint encoding or hand labeling of datasets.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 38 REFERENCES
Toward automatic robot instruction from perception-temporal segmentation of tasks from human hand motion
TLDR
It is shown that by analyzing the fingertip polygon area and the speed of hand movement, a task can be divided into meaningful action segments such as approach object, grasp object, manipulate object, place object, and depart (a special case of the pregrasp phase which signals the termination of the task).
Grasping movements recognition in 3D space using a Bayesian approach
TLDR
An automated system is developed to estimate and recognize two possible types of grasping by the hand movements performed by humans that are tracked by a magnetic tracking device, which can be used to endow a robot with autonomous capabilities.
A new strategy combining empirical and analytical approaches for grasping unknown 3D objects
Learning and generalization of motor skills by learning from demonstration
TLDR
A general approach for learning robotic motor skills from human demonstration is provided and how this framework extends to the control of gripper orientation and finger position and the feasibility of this approach is demonstrated.
Probabilistic representation of 3D object shape by in-hand exploration
TLDR
This work presents a representation of 3D object shape using a probabilistic volumetric map derived from in-hand exploration of both static and non-static objects that show that valid models can be obtained.
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
Learning grasping points with shape context
A hybrid approach for grasping 3D objects
  • A. Sahbani, S. El-Khoury
  • Engineering
    2009 IEEE/RSJ International Conference on Intelligent Robots and Systems
  • 2009
TLDR
A hybrid approach combining empirical and analytical methods is proposed that learns to associate a grasp to an unknown object/task and ensures task-compatibility.
3D hand trajectory segmentation by curvatures and hand orientation for classification through a probabilistic approach
  • D. Faria, J. Dias
  • Computer Science
    2009 IEEE/RSJ International Conference on Intelligent Robots and Systems
  • 2009
TLDR
An application to estimate and classify two possible types of grasping by the reach-to-grasp movements performed by humans, important to understand some human behaviors before the object manipulation and can be used to endow a robot with autonomous capabilities.
Recognition of in-hand manipulation using contact state transition for multifingered robot hand control
...
1
2
3
4
...