(closed) Master Project: Audio-Visual Event Localization with the Humanoid Robot NAO

Short Descrption

The PERCEPTION team investigates the computational principles underlying human-robot interaction. Under this broad topic, this master project will investigate the use of computer vision and audio signal processing methods enabling a robot to localize events that are both seen and heard, such as a group of people engaged in a conversation or in an informal social gathering, and to synthesize appropriate actions, such as turning its had towards a person, or waving to a group of persons. The project will benefit from recent work on sound-source localization, face detection and localization, head pose estimation, audio-visual alignment, and audio-visual clustering performed in the team, as well as of recent work on multimodal scene analysis with a humanoid robot. It will also benefit from the team experience in robot programming.

The project will aim at developing real-time audio-visual algorithms using the humanoid robot NAO and its advanced hardware, software, sensors, and actuators. The project is suitable to a second year master student with very good background in image and signal processing, robotics, and real-time algorithms and programming. The project is part of a larger effort to endow robots with cognitive interaction and is funded by the ERC advanced grant VHIA. To see an example of what was achieved in the recent pas, please visit this page.

The project may start anytime after 1 February 2015 for a period of six months and it could continue with a PhD thesis, which will be fully funded by the VHIA grant.

Information for applicants: Please send your complete CV, university grades, and the names and emails of two recommending persons to radu.horaud@inria.fr. Students enrolled in a French university will receive a monthly net salary of 430€. Students enrolled in another university will receive a monthly net salary of 1100€. Please note that some restrictions apply to non-French students and their admission is conditioned by an approval from the French Ministry of Defense.

References:

Xavier Alameda-Pineda ; Radu Horaud. Vision-Guided Robot Hearing. International Journal of Robotics Research, SAGE, 2014

main.pdf BibTex

Jan Cech, Ravi Mittal, Antoine Deleforge, Jordi Sanchez-Riera, Xavier Alameda-Pineda and Radu Horaud. Active-Speaker Detection and Localization with Microphones and Cameras Embedded into a Robotic HeadIEEE International Conference on Humanoid Robots (HUMANOIDS’13), Oct 2013, Atlanta, USA.

main_final.pdf BibTex

Jordi Sanchez-Riera, Xavier Alameda-Pineda, Johannes Wienke; Antoine Deleforge, Soraya Arias, Jan Cech, Sebastian Wrede and Radu Horaud. Online Multimodal Speaker Detection for Humanoid Robots.  IEEE International Conference on Humanoid Robotics (HUMANOIDS’12), Nov 2012, Osaka, Japan.

Sanchez-Humanoids2012.pdfBibTex

Maxime Janvier; Xavier Alameda-Pineda, Laurent Girin and Radu Horaud. Sound-Event Recognition with a Companion HumanoidIEEE International Conference on Humanoid Robotics (HUMANOIDS’12), Nov 2012, Osaka, Japan.

IROS.pdf BibTex