Abstract:According to the high dynamics of robot soccer competition in RoboCup Middle Size League and the deficiency of the current self-localization methods,a robust self-localization method based on omnidirectional vision is proposed.The method combines the particle filter localization with the matching optimization localization,and a camera parameter auto-adjusting algorithm based on image entropy is also proposed to adapt the output of omnidirectional vision to the dynamic lighting conditions.The experimental results show that global localization can be realized effectively with the proposed method while highly accurate self-localization is achieved in real-time,and robot's self-localization is robust to the highly dynamic environment with occlusion and varying lighting conditions.
[1] 刘伟.RoboCup中型组机器人全景视觉系统设计与实现[D].长沙:国防科学技术大学,2004.Liu Wei.The design and realization of the omni-vision system for RoboCup middle size league robot[D].Changsha:National University of Defense Technology,2004.
[2] Lima P,Bonarini A,Machado C,et al.Omni-directional catadioptric vision for soccer robots[J].Robotics and Autonomous Systems,2001,36(2/3):87-102.
[3] 卢惠民,刘斐,郑志强.一种新的用于足球机器人的全向视觉系统[J].中国图象图形学报,2007,12(7):1243-1248.Lu Huimin,Liu Fei,Zheng Zhiqiang.A novel omni-vision system for soccer robots[J].Journal of Image and Graphics,2007,12(7):1243-1248.
[4] Menegatti E,Pretto A,Scarpa A,et al.Omnidirectional vision scan matching for robot localization in dynamic environments[J].IEEE Transactions on Robotics,2006,22(3):523-535.
[5] Merke A,Welker S,Riedmiller M.Line based robot localization under natural light conditions[C]//ECAI 2004 Workshop on Agents in Dynamic and Real Time Environments.2004.
[6] Lauer M,Lange S,Riedmiller M.Calculating the perfect match:An efficient and accurate approach for robot selflocalization[C]//RoboCup 2005:Robot Soccer World Cup IX.Berlin,Germany:Springer-Verlag,2006:142-153.
[7] Heinemann P,Haase J,Zell A.A novel approach to efficient Monte-Carlo localization in RoboCup[C]//RoboCup 2006:Robot Soccer World Cup X.Berlin,Germany:Springer-Verlag,2007:322-329.
[8] Lu H M,Zhang H,Xiao J H,et al.Arbitrary ball recognition based on omni-directional vision for soccer robots[C]//RoboCup 2008:Robot Soccer World Cup XII.Berlin,Germany:Springer-Verlag,2009:133-144.
[9] Voigtl(a)nder A,Lange S,Lauer M,et al.Real-time 3D ball recognition using perspective and catadioptric cameras[C]//European Conference on Mobile Robots.2007.http://ecmr07.informatik.uni-freiburg.de/proceedings/ECMR07_0067.pdf.
[10] Lu H M,Zheng Z Q,Liu E et al.A robust object recognition method for soccer robots[C]//World Congress on Intelligent Control and Automation.Piscataway,NJ,USA:IEEE,2008:1645-1650.
[11] Lu H.M,Zhang H,Yang S W,et al.A novel camera parameters auto-adjusting method based on image entropy[C]//RoboCup 2009 International Symposium.2009.