A Reliability-Based Particle Filter for Humanoid Robot Self-Localization in RoboCup Standard Platform League

Sensors

Eduardo Munera Sánchez²  Manuel Muñoz Alcobendas²  Juan Fco. Blanes Noguera²  Ginés Benet Gilabert¹ 

[1] Instituto de Automática e Informática Industrial (ai2), Universitat Politecnica de Valencia, P.O.Box 22012, Valencia, Spain;

关键词: humanoid robots;    self-localization;    perception system;    particle filter;    RoboCup SPL;   

DOI  :  10.3390/s131114954

来源: mdpi

【 摘 要 】

This paper deals with the problem of humanoid robot localization and proposes a new method for position estimation that has been developed for the RoboCup Standard Platform League environment. Firstly, a complete vision system has been implemented in the Nao robot platform that enables the detection of relevant field markers. The detection of field markers provides some estimation of distances for the current robot position. To reduce errors in these distance measurements, extrinsic and intrinsic camera calibration procedures have been developed and described. To validate the localization algorithm, experiments covering many of the typical situations that arise during RoboCup games have been developed: ranging from degradation in position estimation to total loss of position (due to falls, ‘kidnapped robot’, or penalization). The self-localization method developed is based on the classical particle filter algorithm. The main contribution of this work is a new particle selection strategy. Our approach reduces the CPU computing time required for each iteration and so eases the limited resource availability problem that is common in robot platforms such as Nao. The experimental results show the quality of the new algorithm in terms of localization and CPU time consumption.

【 授权许可】

CC BY   
© 2013 by the authors; licensee MDPI, Basel, Switzerland.