Control of Nonholonomic Mobile Robot Formations Using Neural Networks

Jagannathan Sarangapani; Travis Alan Dierks

doi:10.1109/ISIC.2007.4450873

Control of Nonholonomic Mobile Robot Formations Using Neural Networks

Jagannathan Sarangapani
, Travis Alan Dierks

Electrical and Computer Engineering

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

Abstract

In this paper the control of formations of multiple nonholonomic mobile robots is attempted by integrating a kinematic controller with a neural network (NN) computed-torque controller. A combined kinematic/torque control law is developed for leader-follower based formation control using backstepping in order to accommodate the dynamics of the robots and the formation in contrast with kinematic-based formation controllers. The NN is introduced to approximate the dynamics of the follower as well as its leader using online weight tuning. It is shown using Lyapunov theory that the errors for the entire formation are uniformly ultimately bounded, and numerical results are provided.

Original language	American English
Journal	Proceedings of the IEEE 22nd International Symposium on Intelligent Control, 2007 (2007, Singapore)
DOIs	https://doi.org/10.1109/ISIC.2007.4450873
State	Published - Oct 1 2007

Keywords

Kinematic/Dynamic Controller
Lyapunov Methods
Mobile Robots
Multi-Robot Systems
Neural Network Torque Controller
Neurocontrollers
Online Weight Tuning
Robot Kinematics

Disciplines

Computer Sciences
Electrical and Computer Engineering

Access to Document

10.1109/ISIC.2007.4450873License: Unspecified

Control of Nonholonomic Mobile Robot Formations Using Neural NetwFinal published version, 375 KBLicense: Unspecified

Cite this

@article{cddecf2c29a449f1aee4844ce9107c80,

title = "Control of Nonholonomic Mobile Robot Formations Using Neural Networks",

abstract = " In this paper the control of formations of multiple nonholonomic mobile robots is attempted by integrating a kinematic controller with a neural network (NN) computed-torque controller. A combined kinematic/torque control law is developed for leader-follower based formation control using backstepping in order to accommodate the dynamics of the robots and the formation in contrast with kinematic-based formation controllers. The NN is introduced to approximate the dynamics of the follower as well as its leader using online weight tuning. It is shown using Lyapunov theory that the errors for the entire formation are uniformly ultimately bounded, and numerical results are provided.",

keywords = "Kinematic/Dynamic Controller, Lyapunov Methods, Mobile Robots, Multi-Robot Systems, Neural Network Torque Controller, Neurocontrollers, Online Weight Tuning, Robot Kinematics",

author = "Jagannathan Sarangapani and Dierks, \{Travis Alan\}",

year = "2007",

month = oct,

day = "1",

doi = "10.1109/ISIC.2007.4450873",

language = "American English",

journal = "Proceedings of the IEEE 22nd International Symposium on Intelligent Control, 2007 (2007, Singapore)",

}

TY - JOUR

T1 - Control of Nonholonomic Mobile Robot Formations Using Neural Networks

AU - Sarangapani, Jagannathan

AU - Dierks, Travis Alan

PY - 2007/10/1

Y1 - 2007/10/1

N2 - In this paper the control of formations of multiple nonholonomic mobile robots is attempted by integrating a kinematic controller with a neural network (NN) computed-torque controller. A combined kinematic/torque control law is developed for leader-follower based formation control using backstepping in order to accommodate the dynamics of the robots and the formation in contrast with kinematic-based formation controllers. The NN is introduced to approximate the dynamics of the follower as well as its leader using online weight tuning. It is shown using Lyapunov theory that the errors for the entire formation are uniformly ultimately bounded, and numerical results are provided.

AB - In this paper the control of formations of multiple nonholonomic mobile robots is attempted by integrating a kinematic controller with a neural network (NN) computed-torque controller. A combined kinematic/torque control law is developed for leader-follower based formation control using backstepping in order to accommodate the dynamics of the robots and the formation in contrast with kinematic-based formation controllers. The NN is introduced to approximate the dynamics of the follower as well as its leader using online weight tuning. It is shown using Lyapunov theory that the errors for the entire formation are uniformly ultimately bounded, and numerical results are provided.

KW - Kinematic/Dynamic Controller

KW - Lyapunov Methods

KW - Mobile Robots

KW - Multi-Robot Systems

KW - Neural Network Torque Controller

KW - Neurocontrollers

KW - Online Weight Tuning

KW - Robot Kinematics

UR - https://scholarsmine.mst.edu/ele_comeng_facwork/1515

U2 - 10.1109/ISIC.2007.4450873

DO - 10.1109/ISIC.2007.4450873

M3 - Article

JO - Proceedings of the IEEE 22nd International Symposium on Intelligent Control, 2007 (2007, Singapore)

JF - Proceedings of the IEEE 22nd International Symposium on Intelligent Control, 2007 (2007, Singapore)

ER -

Control of Nonholonomic Mobile Robot Formations Using Neural Networks

Abstract

Keywords

Disciplines

Access to Document

Other files and links

Fingerprint

Cite this