• Mathematics
  • Published 2010

Learning Motion Patterns from Multiple Observations along the Actions Phases of Manipulative Tasks

@inproceedings{Faria2010LearningMP,
  title={Learning Motion Patterns from Multiple Observations along the Actions Phases of Manipulative Tasks},
  author={Diego R. Faria and Ricardo Martins and Jorge Dias},
  year={2010}
}
In this work, we present a probabilistic approach to find motion patterns in manipulation tasks by looking for similarities among relevant features inside action phases of trajectories. From multiple observations of a specific human movement, we can temporally align all signals to perform a learning process based on selection of relevant features. By analyzing the probability distribution and finding corresponding features among trajectories (i.e. motion patterns), we thus obtain a prototype to… CONTINUE READING

Tables from this paper.

Citations

Publications citing this paper.
SHOWING 1-2 OF 2 CITATIONS

References

Publications referenced by this paper.
SHOWING 1-7 OF 7 REFERENCES

3D hand trajectory segmentation by curvatures and hand orientation for classification through a probabilistic approach

VIEW 3 EXCERPTS

Detecting repeated motion patterns via Dynamic Programming using motion density

VIEW 1 EXCERPT

Learning and generalization of motor skills by learning from demonstration

On Learning, Representing, and Generalizing a Task in a Humanoid Robot