TUTCRIS - Tampereen teknillinen yliopisto

TUTCRIS

Optimizing gaze direction in a visual navigation task

Tutkimustuotosvertaisarvioitu

Yksityiskohdat

AlkuperäiskieliEnglanti
Otsikko2016 IEEE International Conference on Robotics and Automation (ICRA)
KustantajaIEEE
Sivut1427-1432
Sivumäärä6
ISBN (painettu)9781467380263
DOI - pysyväislinkit
TilaJulkaistu - 8 kesäkuuta 2016
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisussa
TapahtumaIEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION -
Kesto: 1 tammikuuta 19001 tammikuuta 2000

Julkaisusarja

Nimi
ISSN (painettu)2152-4092

Conference

ConferenceIEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION
Ajanjakso1/01/001/01/00

Tiivistelmä

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.

Latausten tilastot

Ei tietoja saatavilla