Human motion segmentation using cost weights recovered from inverse optimal control

Jonathan Feng Shun Lin, Vincent Bonnet, Adina M. Panchea, Nacim Ramdani, Gentiane Venture, Dana Kulić

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

8 Citations (Scopus)

Abstract

A common hypothesis in human motor control is that human movement is generated by optimizing with respect to a certain criterion and is task dependent. In this paper, a method to segment human movement by detecting changes to the optimization criterion being used via inverse optimal control is proposed. The control strategy employed by the motor system is hypothesized to be a weighted sum of basis cost functions, with the basis weights changing with changes to the motion objective(s). Continuous time series data of movement is processed using a sliding fixed width window, estimating the basis weights of each cost function for each window by minimizing the Karush-Kuhn-Tucker optimality conditions. The quality of the cost function recovery is verified by evaluating the residual. The successfully estimated basis weights are averaged together to create a set of time varying basis weights that describe the changing control strategy of the motion and can be used to segment the movement with simple thresholds. The proposed algorithm is first demonstrated on simulation data and then demonstrated on a dataset of human subjects performing a series of squatting tasks. The proposed approach reliably identifies the squatting movements, achieving a segmentation accuracy of 84%.

Original languageEnglish
Title of host publication2016 IEEE-RAS 16th international Conference on Humanoid Robots (Humanoids 2016)
EditorsPaul Oh
Place of PublicationPiscataway NJ USA
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages1107-1113
Number of pages7
ISBN (Electronic)9781509047185, 9781509047178
ISBN (Print)9781509047192
DOIs
Publication statusPublished - 30 Dec 2016
Externally publishedYes
EventIEEE-RAS International Conference on Humanoid Robots 2016 - Cancun, Mexico
Duration: 15 Nov 201617 Nov 2016
Conference number: 16th

Publication series

NameIEEE-RAS International Conference on Humanoid Robots
PublisherIEEE, Institute of Electrical and Electronics Engineers
ISSN (Print)2164-0572
ISSN (Electronic)2164-0580

Conference

ConferenceIEEE-RAS International Conference on Humanoid Robots 2016
Abbreviated titleHumanoids 2016
CountryMexico
CityCancun
Period15/11/1617/11/16

Cite this

Lin, J. F. S., Bonnet, V., Panchea, A. M., Ramdani, N., Venture, G., & Kulić, D. (2016). Human motion segmentation using cost weights recovered from inverse optimal control. In P. Oh (Ed.), 2016 IEEE-RAS 16th international Conference on Humanoid Robots (Humanoids 2016) (pp. 1107-1113). [7803409] (IEEE-RAS International Conference on Humanoid Robots). IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/HUMANOIDS.2016.7803409