Navigation functions learning from experiments: Application to anthropomorphic grasping

Ioannis F. Filippidis, Kostas J. Kyriakopoulos, Panagiotis Artemiadis

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

This paper proposes a method to construct Navigation Functions (NF) from experimental trajectories in an unknown environment. We want to approximate an unknown obstacle function and then use it within an NF. When navigating the same destinations with the experiments, this NF should produce the same trajectories as the experiments. This requirement is equivalent to a partial differential equation (PDE). Solving the PDE yields the unknown obstacle function, expressed with spline basis functions. We apply this new method to anthropomorphic grasping, producing automatic trajectories similar to the observed ones. The grasping experiments were performed for a set of different objects, Principal Component Analysis (PCA) allows reduction of the configuration space dimension, where the learning NF method is then applied.

Original languageEnglish (US)
Title of host publicationProceedings - IEEE International Conference on Robotics and Automation
Pages570-575
Number of pages6
DOIs
StatePublished - 2012

Fingerprint

Navigation
Experiments
Trajectories
Partial differential equations
Splines
Principal component analysis

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence
  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Cite this

Filippidis, I. F., Kyriakopoulos, K. J., & Artemiadis, P. (2012). Navigation functions learning from experiments: Application to anthropomorphic grasping. In Proceedings - IEEE International Conference on Robotics and Automation (pp. 570-575). [6225168] https://doi.org/10.1109/ICRA.2012.6225168

Navigation functions learning from experiments : Application to anthropomorphic grasping. / Filippidis, Ioannis F.; Kyriakopoulos, Kostas J.; Artemiadis, Panagiotis.

Proceedings - IEEE International Conference on Robotics and Automation. 2012. p. 570-575 6225168.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Filippidis, IF, Kyriakopoulos, KJ & Artemiadis, P 2012, Navigation functions learning from experiments: Application to anthropomorphic grasping. in Proceedings - IEEE International Conference on Robotics and Automation., 6225168, pp. 570-575. https://doi.org/10.1109/ICRA.2012.6225168
Filippidis IF, Kyriakopoulos KJ, Artemiadis P. Navigation functions learning from experiments: Application to anthropomorphic grasping. In Proceedings - IEEE International Conference on Robotics and Automation. 2012. p. 570-575. 6225168 https://doi.org/10.1109/ICRA.2012.6225168
Filippidis, Ioannis F. ; Kyriakopoulos, Kostas J. ; Artemiadis, Panagiotis. / Navigation functions learning from experiments : Application to anthropomorphic grasping. Proceedings - IEEE International Conference on Robotics and Automation. 2012. pp. 570-575
@inproceedings{a9d2e71fa73c424b89a6e3579a83eb1a,
title = "Navigation functions learning from experiments: Application to anthropomorphic grasping",
abstract = "This paper proposes a method to construct Navigation Functions (NF) from experimental trajectories in an unknown environment. We want to approximate an unknown obstacle function and then use it within an NF. When navigating the same destinations with the experiments, this NF should produce the same trajectories as the experiments. This requirement is equivalent to a partial differential equation (PDE). Solving the PDE yields the unknown obstacle function, expressed with spline basis functions. We apply this new method to anthropomorphic grasping, producing automatic trajectories similar to the observed ones. The grasping experiments were performed for a set of different objects, Principal Component Analysis (PCA) allows reduction of the configuration space dimension, where the learning NF method is then applied.",
author = "Filippidis, {Ioannis F.} and Kyriakopoulos, {Kostas J.} and Panagiotis Artemiadis",
year = "2012",
doi = "10.1109/ICRA.2012.6225168",
language = "English (US)",
isbn = "9781467314039",
pages = "570--575",
booktitle = "Proceedings - IEEE International Conference on Robotics and Automation",

}

TY - GEN

T1 - Navigation functions learning from experiments

T2 - Application to anthropomorphic grasping

AU - Filippidis, Ioannis F.

AU - Kyriakopoulos, Kostas J.

AU - Artemiadis, Panagiotis

PY - 2012

Y1 - 2012

N2 - This paper proposes a method to construct Navigation Functions (NF) from experimental trajectories in an unknown environment. We want to approximate an unknown obstacle function and then use it within an NF. When navigating the same destinations with the experiments, this NF should produce the same trajectories as the experiments. This requirement is equivalent to a partial differential equation (PDE). Solving the PDE yields the unknown obstacle function, expressed with spline basis functions. We apply this new method to anthropomorphic grasping, producing automatic trajectories similar to the observed ones. The grasping experiments were performed for a set of different objects, Principal Component Analysis (PCA) allows reduction of the configuration space dimension, where the learning NF method is then applied.

AB - This paper proposes a method to construct Navigation Functions (NF) from experimental trajectories in an unknown environment. We want to approximate an unknown obstacle function and then use it within an NF. When navigating the same destinations with the experiments, this NF should produce the same trajectories as the experiments. This requirement is equivalent to a partial differential equation (PDE). Solving the PDE yields the unknown obstacle function, expressed with spline basis functions. We apply this new method to anthropomorphic grasping, producing automatic trajectories similar to the observed ones. The grasping experiments were performed for a set of different objects, Principal Component Analysis (PCA) allows reduction of the configuration space dimension, where the learning NF method is then applied.

UR - http://www.scopus.com/inward/record.url?scp=84864433654&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84864433654&partnerID=8YFLogxK

U2 - 10.1109/ICRA.2012.6225168

DO - 10.1109/ICRA.2012.6225168

M3 - Conference contribution

AN - SCOPUS:84864433654

SN - 9781467314039

SP - 570

EP - 575

BT - Proceedings - IEEE International Conference on Robotics and Automation

ER -