Imitating human reaching motions using physically inspired optimization principles

S. Albrecht; K. Ramírez-Amaro; F. Ruiz-Ugalde; D. Weikersdorfer; M. Leibold; M. Ulbrich; M. Beetz

doi:10.1109/Humanoids.2011.6100856

Imitating human reaching motions using physically inspired optimization principles

S. Albrecht, K. Ramírez-Amaro, F. Ruiz-Ugalde, D. Weikersdorfer, M. Leibold, M. Ulbrich, M. Beetz

Chair of Mathematical Optimization

Technical University of Munich

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

69 Scopus citations

Abstract

We present an end-to-end framework which equips robots with the capability to perform reaching motions in a natural human-like fashion. A markerless, high-accuracy, model-based human motion tracker is used to observe how humans perform everyday activities in real-world scenarios. The obtained trajectories are clustered to represent different types of manipulation and reaching motions occurring in a kitchen environment. Using bilevel optimization methods a combination of physically inspired optimization principles is determined that describes the human motions best. For humanoid robots like the iCub these principles are used to compute reaching motion trajectories which are similar to human behavior and respect the individual requirements of the robotic hardware.

Original language	English
Title of host publication	2011 11th IEEE-RAS International Conference on Humanoid Robots, HUMANOIDS 2011
Pages	602-607
Number of pages	6
DOIs	https://doi.org/10.1109/Humanoids.2011.6100856
State	Published - 2011
Event	2011 11th IEEE-RAS International Conference on Humanoid Robots, HUMANOIDS 2011 - Bled, Slovenia Duration: 26 Oct 2011 → 28 Oct 2011

Publication series

Name	IEEE-RAS International Conference on Humanoid Robots
ISSN (Print)	2164-0572
ISSN (Electronic)	2164-0580

Conference

Conference	2011 11th IEEE-RAS International Conference on Humanoid Robots, HUMANOIDS 2011
Country/Territory	Slovenia
City	Bled
Period	26/10/11 → 28/10/11

Access to Document

10.1109/Humanoids.2011.6100856

Cite this

Albrecht, S., Ramírez-Amaro, K., Ruiz-Ugalde, F., Weikersdorfer, D., Leibold, M., Ulbrich, M., & Beetz, M. (2011). Imitating human reaching motions using physically inspired optimization principles. In 2011 11th IEEE-RAS International Conference on Humanoid Robots, HUMANOIDS 2011 (pp. 602-607). Article 6100856 (IEEE-RAS International Conference on Humanoid Robots). https://doi.org/10.1109/Humanoids.2011.6100856

@inproceedings{cc3c685ae2c74b6b8e7f5ad0c451a8c7,

title = "Imitating human reaching motions using physically inspired optimization principles",

abstract = "We present an end-to-end framework which equips robots with the capability to perform reaching motions in a natural human-like fashion. A markerless, high-accuracy, model-based human motion tracker is used to observe how humans perform everyday activities in real-world scenarios. The obtained trajectories are clustered to represent different types of manipulation and reaching motions occurring in a kitchen environment. Using bilevel optimization methods a combination of physically inspired optimization principles is determined that describes the human motions best. For humanoid robots like the iCub these principles are used to compute reaching motion trajectories which are similar to human behavior and respect the individual requirements of the robotic hardware.",

author = "S. Albrecht and K. Ram{\'i}rez-Amaro and F. Ruiz-Ugalde and D. Weikersdorfer and M. Leibold and M. Ulbrich and M. Beetz",

year = "2011",

doi = "10.1109/Humanoids.2011.6100856",

language = "English",

isbn = "9781612848679",

series = "IEEE-RAS International Conference on Humanoid Robots",

pages = "602--607",

booktitle = "2011 11th IEEE-RAS International Conference on Humanoid Robots, HUMANOIDS 2011",

note = "2011 11th IEEE-RAS International Conference on Humanoid Robots, HUMANOIDS 2011 ; Conference date: 26-10-2011 Through 28-10-2011",

}

Albrecht, S, Ramírez-Amaro, K, Ruiz-Ugalde, F, Weikersdorfer, D, Leibold, M, Ulbrich, M & Beetz, M 2011, Imitating human reaching motions using physically inspired optimization principles. in 2011 11th IEEE-RAS International Conference on Humanoid Robots, HUMANOIDS 2011., 6100856, IEEE-RAS International Conference on Humanoid Robots, pp. 602-607, 2011 11th IEEE-RAS International Conference on Humanoid Robots, HUMANOIDS 2011, Bled, Slovenia, 26/10/11. https://doi.org/10.1109/Humanoids.2011.6100856

Imitating human reaching motions using physically inspired optimization principles. / Albrecht, S.; Ramírez-Amaro, K.; Ruiz-Ugalde, F. et al.
2011 11th IEEE-RAS International Conference on Humanoid Robots, HUMANOIDS 2011. 2011. p. 602-607 6100856 (IEEE-RAS International Conference on Humanoid Robots).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Imitating human reaching motions using physically inspired optimization principles

AU - Albrecht, S.

AU - Ramírez-Amaro, K.

AU - Ruiz-Ugalde, F.

AU - Weikersdorfer, D.

AU - Leibold, M.

AU - Ulbrich, M.

AU - Beetz, M.

PY - 2011

Y1 - 2011

N2 - We present an end-to-end framework which equips robots with the capability to perform reaching motions in a natural human-like fashion. A markerless, high-accuracy, model-based human motion tracker is used to observe how humans perform everyday activities in real-world scenarios. The obtained trajectories are clustered to represent different types of manipulation and reaching motions occurring in a kitchen environment. Using bilevel optimization methods a combination of physically inspired optimization principles is determined that describes the human motions best. For humanoid robots like the iCub these principles are used to compute reaching motion trajectories which are similar to human behavior and respect the individual requirements of the robotic hardware.

AB - We present an end-to-end framework which equips robots with the capability to perform reaching motions in a natural human-like fashion. A markerless, high-accuracy, model-based human motion tracker is used to observe how humans perform everyday activities in real-world scenarios. The obtained trajectories are clustered to represent different types of manipulation and reaching motions occurring in a kitchen environment. Using bilevel optimization methods a combination of physically inspired optimization principles is determined that describes the human motions best. For humanoid robots like the iCub these principles are used to compute reaching motion trajectories which are similar to human behavior and respect the individual requirements of the robotic hardware.

UR - http://www.scopus.com/inward/record.url?scp=84856354699&partnerID=8YFLogxK

U2 - 10.1109/Humanoids.2011.6100856

DO - 10.1109/Humanoids.2011.6100856

M3 - Conference contribution

AN - SCOPUS:84856354699

SN - 9781612848679

T3 - IEEE-RAS International Conference on Humanoid Robots

SP - 602

EP - 607

BT - 2011 11th IEEE-RAS International Conference on Humanoid Robots, HUMANOIDS 2011

T2 - 2011 11th IEEE-RAS International Conference on Humanoid Robots, HUMANOIDS 2011

Y2 - 26 October 2011 through 28 October 2011

ER -

Albrecht S, Ramírez-Amaro K, Ruiz-Ugalde F, Weikersdorfer D, Leibold M, Ulbrich M et al. Imitating human reaching motions using physically inspired optimization principles. In 2011 11th IEEE-RAS International Conference on Humanoid Robots, HUMANOIDS 2011. 2011. p. 602-607. 6100856. (IEEE-RAS International Conference on Humanoid Robots). doi: 10.1109/Humanoids.2011.6100856

Imitating human reaching motions using physically inspired optimization principles

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this