Towards Crossmodal Learning for Smooth Multimodal Attention Orientation

Frederik Haarslev, David Docherty , Stefan-Daniel Suvei, William Kristian Juel, Leon Bodenhagen, Danish Shaikh, Norbert Krüger, Poramate Manoonpong

Publikation: Kapitel i bog/rapport/konference-proceedingKonferencebidrag i proceedingsForskningpeer review

Abstrakt

Orienting attention towards another person of interest is a fundamental social behaviour prevalent in human-human interaction and crucial in human-robot interaction. This orientation behaviour is often governed by the received audio-visual stimuli. We present an adaptive neural circuit for multisensory attention orientation that combines auditory and visual directional cues. The circuit learns to integrate sound direction cues, extracted via a model of the peripheral auditory system of lizards, with visual directional cues via deep learning based object detection. We implement the neural circuit on a robot and demonstrate that integrating multisensory information via the circuit generates appropriate motor velocity commands that control the robot’s orientation movements. We experimentally validate the adaptive neural circuit for co-located human target and a loudspeaker emitting a fixed tone.
OriginalsprogEngelsk
TitelSocial Robotics : Proceedings of the 10th International Conference, ICSR 2018
RedaktørerShuzhi Sam Ge, John-John Cabibihan, Miguel A. Salichs, Elizabeth Broadbent, Hongsheng He, Alan R. Wagner, Álvaro Castro-González
ForlagSpringer
Publikationsdato2018
Sider318-328
ISBN (Trykt)978-3-030-05203-4
ISBN (Elektronisk)978-3-030-05204-1
DOI
StatusUdgivet - 2018
Begivenhed10th International Conference on Social Robotics - Qingdao, Kina
Varighed: 28. nov. 201830. nov. 2018
http://uconf.org/ICSR2018/index.html

Konference

Konference10th International Conference on Social Robotics
Land/OmrådeKina
ByQingdao
Periode28/11/201830/11/2018
Internetadresse
NavnLecture Notes in Computer Science
Vol/bind11357
ISSN0302-9743
NavnLecture Notes in Artificial Intelligence
Vol/bind11357

Fingeraftryk

Dyk ned i forskningsemnerne om 'Towards Crossmodal Learning for Smooth Multimodal Attention Orientation'. Sammen danner de et unikt fingeraftryk.

Citationsformater