Data-driven multi-stage motion planning of parallel kinematic machines

Amar Khoukhi

doi:10.1109/TCST.2009.2036600

Data-driven multi-stage motion planning of parallel kinematic machines

Amar Khoukhi^*

^*Corresponding author for this work

King Fahd University of Petroleum & Minerals

Research output: Contribution to journal › Article › peer-review

22 Scopus citations

Abstract

A multistage data-driven neuro-fuzzy system is considered for the multiobjective trajectory planning of Parallel Kinematic Machines (PKMs). This system is developed in two major steps. First, an offline planning based on robot kinematic and dynamic models, including actuators, is performed to generate a large dataset of trajectories, covering most of the robot workspace and minimizing time and energy, while avoiding singularities and limits on joint angles, rates, accelerations, and torques. An augmented Lagrangian technique is implemented on a decoupled form of the PKM dynamics in order to solve the resulting nonlinear constrained optimal control problem. Then, the outcomes of the offline-planning are used to build a data-driven neuro-fuzzy inference system to learn and capture the desired dynamic behavior of the PKM. Once this system is optimized, it is used to achieve near-optimal online planning with a reasonable time complexity. Simulations proving the effectiveness of this approach on a 2-degrees-of-freedom planar PKM are given and discussed.

Original language	English
Article number	5357404
Pages (from-to)	1381-1389
Number of pages	9
Journal	IEEE Transactions on Control Systems Technology
Volume	18
Issue number	6
DOIs	https://doi.org/10.1109/TCST.2009.2036600
State	Published - Nov 2010

Bibliographical note

Funding Information:
Manuscript received May 21, 2009; revised August 11, 2009. Manuscript received in final form November 05, 2009. First published December 22, 2009; current version published October 22, 2010. Recommended by Associate Editor C.-Y. Su. This work was supported by King Fahd University of Petroleum and Minerals.

Keywords

Augmented Lagrangian
data-driven neuro-fuzzy systems
decoupling
multiobjective trajectory planning
parallel kinematic machines
subtractive clustering

ASJC Scopus subject areas

Control and Systems Engineering
Electrical and Electronic Engineering

Access to Document

10.1109/TCST.2009.2036600

Cite this

@article{4b46277bb0c64c88b0ee0ac0412ee54b,

title = "Data-driven multi-stage motion planning of parallel kinematic machines",

abstract = "A multistage data-driven neuro-fuzzy system is considered for the multiobjective trajectory planning of Parallel Kinematic Machines (PKMs). This system is developed in two major steps. First, an offline planning based on robot kinematic and dynamic models, including actuators, is performed to generate a large dataset of trajectories, covering most of the robot workspace and minimizing time and energy, while avoiding singularities and limits on joint angles, rates, accelerations, and torques. An augmented Lagrangian technique is implemented on a decoupled form of the PKM dynamics in order to solve the resulting nonlinear constrained optimal control problem. Then, the outcomes of the offline-planning are used to build a data-driven neuro-fuzzy inference system to learn and capture the desired dynamic behavior of the PKM. Once this system is optimized, it is used to achieve near-optimal online planning with a reasonable time complexity. Simulations proving the effectiveness of this approach on a 2-degrees-of-freedom planar PKM are given and discussed.",

keywords = "Augmented Lagrangian, data-driven neuro-fuzzy systems, decoupling, multiobjective trajectory planning, parallel kinematic machines, subtractive clustering",

author = "Amar Khoukhi",

note = "Funding Information: Manuscript received May 21, 2009; revised August 11, 2009. Manuscript received in final form November 05, 2009. First published December 22, 2009; current version published October 22, 2010. Recommended by Associate Editor C.-Y. Su. This work was supported by King Fahd University of Petroleum and Minerals.",

year = "2010",

month = nov,

doi = "10.1109/TCST.2009.2036600",

language = "English",

volume = "18",

pages = "1381--1389",

journal = "IEEE Transactions on Control Systems Technology",

issn = "1063-6536",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "6",

}

TY - JOUR

T1 - Data-driven multi-stage motion planning of parallel kinematic machines

AU - Khoukhi, Amar

N1 - Funding Information: Manuscript received May 21, 2009; revised August 11, 2009. Manuscript received in final form November 05, 2009. First published December 22, 2009; current version published October 22, 2010. Recommended by Associate Editor C.-Y. Su. This work was supported by King Fahd University of Petroleum and Minerals.

PY - 2010/11

Y1 - 2010/11

N2 - A multistage data-driven neuro-fuzzy system is considered for the multiobjective trajectory planning of Parallel Kinematic Machines (PKMs). This system is developed in two major steps. First, an offline planning based on robot kinematic and dynamic models, including actuators, is performed to generate a large dataset of trajectories, covering most of the robot workspace and minimizing time and energy, while avoiding singularities and limits on joint angles, rates, accelerations, and torques. An augmented Lagrangian technique is implemented on a decoupled form of the PKM dynamics in order to solve the resulting nonlinear constrained optimal control problem. Then, the outcomes of the offline-planning are used to build a data-driven neuro-fuzzy inference system to learn and capture the desired dynamic behavior of the PKM. Once this system is optimized, it is used to achieve near-optimal online planning with a reasonable time complexity. Simulations proving the effectiveness of this approach on a 2-degrees-of-freedom planar PKM are given and discussed.

AB - A multistage data-driven neuro-fuzzy system is considered for the multiobjective trajectory planning of Parallel Kinematic Machines (PKMs). This system is developed in two major steps. First, an offline planning based on robot kinematic and dynamic models, including actuators, is performed to generate a large dataset of trajectories, covering most of the robot workspace and minimizing time and energy, while avoiding singularities and limits on joint angles, rates, accelerations, and torques. An augmented Lagrangian technique is implemented on a decoupled form of the PKM dynamics in order to solve the resulting nonlinear constrained optimal control problem. Then, the outcomes of the offline-planning are used to build a data-driven neuro-fuzzy inference system to learn and capture the desired dynamic behavior of the PKM. Once this system is optimized, it is used to achieve near-optimal online planning with a reasonable time complexity. Simulations proving the effectiveness of this approach on a 2-degrees-of-freedom planar PKM are given and discussed.

KW - Augmented Lagrangian

KW - data-driven neuro-fuzzy systems

KW - decoupling

KW - multiobjective trajectory planning

KW - parallel kinematic machines

KW - subtractive clustering

UR - https://www.scopus.com/pages/publications/77954471746

U2 - 10.1109/TCST.2009.2036600

DO - 10.1109/TCST.2009.2036600

M3 - Article

AN - SCOPUS:77954471746

SN - 1063-6536

VL - 18

SP - 1381

EP - 1389

JO - IEEE Transactions on Control Systems Technology

JF - IEEE Transactions on Control Systems Technology

IS - 6

M1 - 5357404

ER -

Data-driven multi-stage motion planning of parallel kinematic machines

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this