Tampere University of Technology

TUTCRIS Research Portal

Optimizing gaze direction in a visual navigation task

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Details

Original languageEnglish
Title of host publication2016 IEEE International Conference on Robotics and Automation (ICRA)
PublisherIEEE
Pages1427-1432
Number of pages6
ISBN (Print)9781467380263
DOIs
Publication statusPublished - 8 Jun 2016
Publication typeA4 Article in a conference publication
EventIEEE International Conference on Robotics and Automation -
Duration: 1 Jan 19001 Jan 2000

Publication series

Name
ISSN (Print)2152-4092

Conference

ConferenceIEEE International Conference on Robotics and Automation
Period1/01/001/01/00

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.

Downloads statistics

No data available