Optimizing gaze direction in a visual navigation task

Tuomas Välimäki; Risto Ritala

doi:10.1109/ICRA.2016.7487276

Optimizing gaze direction in a visual navigation task

Tuomas Välimäki, Risto Ritala

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

3 Citations (Scopus)

56 Downloads (Pure)

Abstract

Navigation in an unknown environment consists of multiple separable subtasks, such as collecting information about the surroundings and navigating to the current goal. In the case of pure visual navigation, all these subtasks need to utilize the same vision system, and therefore a way to optimally control the direction of focus is needed. We present a case study, where we model the active sensing problem of directing the gaze of a mobile robot with three machine vision cameras as a partially observable Markov decision process (POMDP) using a mutual information (MI) based reward function. The key aspect of the solution is that the cameras are dynamically used either in monocular or stereo configuration. The benefits of using the proposed active sensing implementation are demonstrated with simulations and experiments on a real robot.

Original language	English
Title of host publication	2016 IEEE International Conference on Robotics and Automation (ICRA)
Publisher	IEEE
Pages	1427-1432
Number of pages	6
ISBN (Print)	9781467380263
DOIs	https://doi.org/10.1109/ICRA.2016.7487276
Publication status	Published - 8 Jun 2016
Publication type	A4 Article in conference proceedings
Event	IEEE International Conference on Robotics and Automation - Duration: 1 Jan 1900 → 1 Jan 2000

Publication series

Name
ISSN (Print)	2152-4092

Conference

Conference	IEEE International Conference on Robotics and Automation
Period	1/01/00 → 1/01/00

Publication forum classification

Publication forum level 1

ASJC Scopus subject areas

Software
Artificial Intelligence
Control and Systems Engineering
Electrical and Electronic Engineering

Access to Document

10.1109/ICRA.2016.7487276

Välimäki, Ritala, (2016), Optimizing gaze direction in a visual navigation task
© 2016 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Accepted author manuscript, 1.37 MB

http://urn.fi/URN:NBN:fi:tty-201609304574

Cite this

@inproceedings{132046c899df479fa0f317aa063a8439,

title = "Optimizing gaze direction in a visual navigation task",

abstract = "Navigation in an unknown environment consists of multiple separable subtasks, such as collecting information about the surroundings and navigating to the current goal. In the case of pure visual navigation, all these subtasks need to utilize the same vision system, and therefore a way to optimally control the direction of focus is needed. We present a case study, where we model the active sensing problem of directing the gaze of a mobile robot with three machine vision cameras as a partially observable Markov decision process (POMDP) using a mutual information (MI) based reward function. The key aspect of the solution is that the cameras are dynamically used either in monocular or stereo configuration. The benefits of using the proposed active sensing implementation are demonstrated with simulations and experiments on a real robot.",

author = "Tuomas V{\"a}lim{\"a}ki and Risto Ritala",

year = "2016",

month = jun,

day = "8",

doi = "10.1109/ICRA.2016.7487276",

language = "English",

isbn = "9781467380263",

publisher = "IEEE",

pages = "1427--1432",

booktitle = "2016 IEEE International Conference on Robotics and Automation (ICRA)",

note = "IEEE International Conference on Robotics and Automation ; Conference date: 01-01-1900 Through 01-01-2000",

}

TY - GEN

T1 - Optimizing gaze direction in a visual navigation task

AU - Välimäki, Tuomas

AU - Ritala, Risto

PY - 2016/6/8

Y1 - 2016/6/8

N2 - Navigation in an unknown environment consists of multiple separable subtasks, such as collecting information about the surroundings and navigating to the current goal. In the case of pure visual navigation, all these subtasks need to utilize the same vision system, and therefore a way to optimally control the direction of focus is needed. We present a case study, where we model the active sensing problem of directing the gaze of a mobile robot with three machine vision cameras as a partially observable Markov decision process (POMDP) using a mutual information (MI) based reward function. The key aspect of the solution is that the cameras are dynamically used either in monocular or stereo configuration. The benefits of using the proposed active sensing implementation are demonstrated with simulations and experiments on a real robot.

AB - Navigation in an unknown environment consists of multiple separable subtasks, such as collecting information about the surroundings and navigating to the current goal. In the case of pure visual navigation, all these subtasks need to utilize the same vision system, and therefore a way to optimally control the direction of focus is needed. We present a case study, where we model the active sensing problem of directing the gaze of a mobile robot with three machine vision cameras as a partially observable Markov decision process (POMDP) using a mutual information (MI) based reward function. The key aspect of the solution is that the cameras are dynamically used either in monocular or stereo configuration. The benefits of using the proposed active sensing implementation are demonstrated with simulations and experiments on a real robot.

U2 - 10.1109/ICRA.2016.7487276

DO - 10.1109/ICRA.2016.7487276

M3 - Conference contribution

AN - SCOPUS:84977478616

SN - 9781467380263

SP - 1427

EP - 1432

BT - 2016 IEEE International Conference on Robotics and Automation (ICRA)

PB - IEEE

T2 - IEEE International Conference on Robotics and Automation

Y2 - 1 January 1900 through 1 January 2000

ER -

Optimizing gaze direction in a visual navigation task

Abstract

Publication series

Conference

Publication forum classification

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this