Inverse optimal control for multiphase cost functions

Wanxin Jin, Dana Kulic, Jonathan Feng-Shun Lin, Shaoshuai Mou, Sandra Hirche

Research output: Contribution to journalArticleResearchpeer-review

Abstract

In this paper, we consider a dynamical system whose trajectory is a result of minimizing a multiphase cost function. The multiphase cost function is assumed to be a weighted sum of specified features (or basis functions) with phase-dependent weights that switch at some unknown phase transition points. A new inverse optimal control approach for recovering the cost weights of each phase and estimating the phase transition points is proposed. The key idea is to use a length-adapted window moving along the observed trajectory, where the window length is determined by finding the minimal observation length that suffices for a successful cost weight recovery. The effectiveness of the proposed method is first evaluated on a simulated robot arm, and then, demonstrated on a dataset of human participants performing a series of squatting tasks. The results demonstrate that the proposed method reliably retrieves the cost function of each phase and segments each phase of motion from the trajectory with a segmentation accuracy above 90%.
Original languageEnglish
Number of pages12
JournalIEEE Transactions on Robotics
DOIs
Publication statusAccepted/In press - 29 Jul 2019

Cite this

Jin, Wanxin ; Kulic, Dana ; Lin, Jonathan Feng-Shun ; Mou, Shaoshuai ; Hirche, Sandra. / Inverse optimal control for multiphase cost functions. In: IEEE Transactions on Robotics. 2019.
@article{ec6911528e6146ccb9b1f4a11e1e5f0e,
title = "Inverse optimal control for multiphase cost functions",
abstract = "In this paper, we consider a dynamical system whose trajectory is a result of minimizing a multiphase cost function. The multiphase cost function is assumed to be a weighted sum of specified features (or basis functions) with phase-dependent weights that switch at some unknown phase transition points. A new inverse optimal control approach for recovering the cost weights of each phase and estimating the phase transition points is proposed. The key idea is to use a length-adapted window moving along the observed trajectory, where the window length is determined by finding the minimal observation length that suffices for a successful cost weight recovery. The effectiveness of the proposed method is first evaluated on a simulated robot arm, and then, demonstrated on a dataset of human participants performing a series of squatting tasks. The results demonstrate that the proposed method reliably retrieves the cost function of each phase and segments each phase of motion from the trajectory with a segmentation accuracy above 90{\%}.",
author = "Wanxin Jin and Dana Kulic and Lin, {Jonathan Feng-Shun} and Shaoshuai Mou and Sandra Hirche",
year = "2019",
month = "7",
day = "29",
doi = "10.1109/TRO.2019.2926388",
language = "English",
journal = "IEEE Transactions on Robotics",
issn = "1552-3098",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",

}

Inverse optimal control for multiphase cost functions. / Jin, Wanxin; Kulic, Dana; Lin, Jonathan Feng-Shun; Mou, Shaoshuai; Hirche, Sandra.

In: IEEE Transactions on Robotics, 29.07.2019.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - Inverse optimal control for multiphase cost functions

AU - Jin, Wanxin

AU - Kulic, Dana

AU - Lin, Jonathan Feng-Shun

AU - Mou, Shaoshuai

AU - Hirche, Sandra

PY - 2019/7/29

Y1 - 2019/7/29

N2 - In this paper, we consider a dynamical system whose trajectory is a result of minimizing a multiphase cost function. The multiphase cost function is assumed to be a weighted sum of specified features (or basis functions) with phase-dependent weights that switch at some unknown phase transition points. A new inverse optimal control approach for recovering the cost weights of each phase and estimating the phase transition points is proposed. The key idea is to use a length-adapted window moving along the observed trajectory, where the window length is determined by finding the minimal observation length that suffices for a successful cost weight recovery. The effectiveness of the proposed method is first evaluated on a simulated robot arm, and then, demonstrated on a dataset of human participants performing a series of squatting tasks. The results demonstrate that the proposed method reliably retrieves the cost function of each phase and segments each phase of motion from the trajectory with a segmentation accuracy above 90%.

AB - In this paper, we consider a dynamical system whose trajectory is a result of minimizing a multiphase cost function. The multiphase cost function is assumed to be a weighted sum of specified features (or basis functions) with phase-dependent weights that switch at some unknown phase transition points. A new inverse optimal control approach for recovering the cost weights of each phase and estimating the phase transition points is proposed. The key idea is to use a length-adapted window moving along the observed trajectory, where the window length is determined by finding the minimal observation length that suffices for a successful cost weight recovery. The effectiveness of the proposed method is first evaluated on a simulated robot arm, and then, demonstrated on a dataset of human participants performing a series of squatting tasks. The results demonstrate that the proposed method reliably retrieves the cost function of each phase and segments each phase of motion from the trajectory with a segmentation accuracy above 90%.

U2 - 10.1109/TRO.2019.2926388

DO - 10.1109/TRO.2019.2926388

M3 - Article

JO - IEEE Transactions on Robotics

JF - IEEE Transactions on Robotics

SN - 1552-3098

ER -