Deep Reinforcement Learning for Audio-Visual Gaze Control - Archive ouverte HAL Access content directly
Conference Papers Year :

Deep Reinforcement Learning for Audio-Visual Gaze Control

(1) , (1) , (1) , (1)
1

Abstract

We address the problem of audiovisual gaze control in the specific context of human-robot interaction, namely how controlled robot motions are combined with visual and acoustic observations in order to direct the robot head towards targets of interest. The paper has the following contributions: (i) a novel audiovisual fusion framework that is well suited for controlling the gaze of a robotic head; (ii) a reinforcement learning (RL) formulation for the gaze control problem, using a reward function based on the available temporal sequence of camera and microphone observations; and (iii) several deep architectures that allow to experiment with early and late fusion of audio and visual data. We introduce a simulated environment that enables us to learn the proposed deep RL model without the need of spending hours of tedious interaction. By thoroughly experimenting on a publicly available dataset and on a real robot, we provide empirical evidence that our method achieves state-of-the-art performance.
Fichier principal
Vignette du fichier
main.pdf (3.97 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01851738 , version 1 (30-07-2018)

Identifiers

Cite

Stéphane Lathuilière, Benoit Massé, Pablo Mesejo, Radu Horaud. Deep Reinforcement Learning for Audio-Visual Gaze Control. IROS 2018 - IEEE/RSJ International Conference on Intelligent Robots and Systems, Oct 2018, Madrid, Spain. pp.1555-1562, ⟨10.1109/IROS.2018.8594327⟩. ⟨hal-01851738⟩
321 View
461 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More