Long-term robot motion planning for active sound source localization with Monte Carlo tree search

We consider the problem of controlling a mobile robot in order to localize a sound source. A microphone array can provide the robot with information on source localization. By combining this information with the movements of the robot, the localization accuracy can be improved. However, random robot motion or short-term planning may not result in optimal localization. In this paper, we propose an optimal long-term robot motion planning algorithm for active source localization. We introduce a Monte Carlo tree search (MCTS) method to find a sequence of robot actions that minimize the entropy of the belief on the source location. A tree of possible robot movements which balances between exploration and exploitation is first constructed. Then, the movement that leads to minimum uncertainty is selected and executed. Experiments and statistical results show the effectiveness of our proposed method on improving sound source localization in the long term compared to other motion planning methods.

[1]  Eric Sommerlade,et al.  Information-theoretic active scene exploration , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[2]  Kai Song,et al.  Olfaction and Hearing Based Mobile Robot Navigation for Odor/Sound Source Search , 2011, Sensors.

[3]  Hiroaki Kitano,et al.  Robot recognizes three simultaneous speech by active audition , 2003, 2003 IEEE International Conference on Robotics and Automation (Cat. No.03CH37422).

[4]  Hiroshi G. Okuno,et al.  Robot audition: Its rise and perspectives , 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[5]  Gabriel Bustamante,et al.  Towards information-based feedback control for binaural active localization , 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[6]  Demis Hassabis,et al.  Mastering the game of Go with deep neural networks and tree search , 2016, Nature.

[7]  Boaz Rafaely,et al.  Enhanced robot audition by dynamic acoustic sensing in moving humanoids , 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[8]  Hiroshi Mizoguchi,et al.  Multiple Sound Source Mapping for a Mobile Robot by Self-motion Triangulation , 2006, 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[9]  Hiroaki Kitano,et al.  Active Audition for Humanoid , 2000, AAAI/IAAI.

[10]  Eric Martinson,et al.  Discovery of sound sources by an autonomous mobile robot , 2009, Auton. Robots.

[11]  Pieter Spronck,et al.  Monte-Carlo Tree Search: A New Framework for Game AI , 2008, AIIDE.

[12]  François Chaumette,et al.  Sound-based control with two microphones , 2015, 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[13]  Hugh F. Durrant-Whyte,et al.  On entropy approximation for Gaussian mixture random vectors , 2008, 2008 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems.

[14]  Alastair H. Moore,et al.  Towards Informative Path Planning for Acoustic SLAM , 2016 .

[15]  Ivan Markovic,et al.  Active speaker localization with circular likelihoods and bootstrap filtering , 2013, 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[16]  B. P. DeJong.  Auditory occupancy grids with a mobile robot , 2012 .

[17]  Radu Horaud,et al.  Active hearing, active speaking , 2007 .

[18]  Jan Willemson,et al.  Improved Monte-Carlo Search , 2006 .

[19]  Erik Berglund,et al.  Sound source localisation through active audition , 2005, 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[20]  Simon M. Lucas,et al.  A Survey of Monte Carlo Tree Search Methods , 2012, IEEE Transactions on Computational Intelligence and AI in Games.

[21]  Hiroshi G. Okuno,et al.  Design and Implementation of Robot Audition System 'HARK' — Open Source Software for Listening to Three Simultaneous Speakers , 2010, Adv. Robotics.

[22]  Eric Martinson,et al.  Auditory Evidence Grids , 2006, 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[23]  François Charpillet,et al.  Localizing an intermittent and moving sound source using a mobile robot , 2016, 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[24]  Alban Portello,et al.  Active localization of an intermittent sound source from a moving binaural sensor , 2014 .

[25]  Walter Kellermann,et al.  An adaptive microphone array topology for target signal extraction with humanoid robots , 2014, 2014 14th International Workshop on Acoustic Signal Enhancement (IWAENC).

[26]  Martin Cooke,et al.  Motion strategies for binaural localisation of speech sources in azimuth and distance by artificial listeners , 2011, Speech Commun..

[27]  François Charpillet,et al.  Audio source localization by optimal control of a mobile robot , 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).