粒子滤波与ORB特征检测结合的移动机器人定位算法
|
摘要
针对机器人绑架后的重定位问题,提出了将粒子滤波与图像ORB(oriented FAST and rotated BRIEF)特征匹配结合起来的全局定位算法。机器人被绑架后,由运动模型预测产生的粒子集将不能正确估计机器人位姿。方法通过加入相机观测结果来修正粒子集。首先基于相机图像ORB特征匹配检测机器人所在区域,然后在相机关联的栅格子地图内撒粒子,最后通过粒子滤波的观测更新和重采样使粒子逐渐收敛实现重定位。实验证明:本文方法能够解决机器人绑架问题,在时间效率上优于加入随机粒子的自适应蒙特—卡罗定位算法,且具有更低定位误差。
Aiming at the problem of relocalization after robot abduction,a global localization algorithm based on particle filtering and image oriented FAST and rotated BRIEF(ORB) feature matching is proposed. When the problems occur,the set of particles predicted by the motion model cannot correctly estimate the pose of the robot.The particle set is modified by adding observation results of the camera. The location of the robot is detected based on ORB feature matching of the camera image. The particles are generated in the grid map area associated with the camera. The relocalization is achieved by observation update and re-sampling to gradually converge the particles.The experimental results show that the proposed algorithm can solve the kidnapped robot problem and is superior to the adaptive Monte Carlo localization(AMCL) algorithm with random particles in terms of time efficiency,and it has a lower positioning error.
Aiming at the problem of relocalization after robot abduction,a global localization algorithm based on particle filtering and image oriented FAST and rotated BRIEF(ORB) feature matching is proposed. When the problems occur,the set of particles predicted by the motion model cannot correctly estimate the pose of the robot.The particle set is modified by adding observation results of the camera. The location of the robot is detected based on ORB feature matching of the camera image. The particles are generated in the grid map area associated with the camera. The relocalization is achieved by observation update and re-sampling to gradually converge the particles.The experimental results show that the proposed algorithm can solve the kidnapped robot problem and is superior to the adaptive Monte Carlo localization(AMCL) algorithm with random particles in terms of time efficiency,and it has a lower positioning error.
引文
[1]THRUN S,FOX D,BURGARD W,et al.Robust Monte Carlo localization for mobile robots[J].Artificial Intelligence,2001,128(1-2):99-141.
[2]MAIR E,HAGER G D,BURSCHKA D,et al.Adaptive and generic corner detection based on the accelerated segment test[C]∥European Conference on Computer Vision,Springer,Berlin,Heidelberg,2010:183-196.
[3]RUBLEE E,RABAUD V,KONOLIGE K,et al.ORB:An efficient alternative to SIFT or SURF[C]∥IEEE International Conference on Computer Vision,IEEE,2012:2564-2571.
[4]MA L,LIN Y,CUI Y,et al.Vision-based positioning method based on landmark using multiple calibration lines[C]∥Proceedings of the 2016 International Conference on Communications,Signal Processing,and Systems,Springer,2017:471.
[5]FOX D,THRUN S,BURGARD W,et al.Particle filters for mobile robot localization[M].New York:Springer,2001:401-428.
[6]BUKHORI I,ISMAIL Z H.Detection of kidnapped robot problem in Monte Carlo localization based on the natural displacement of the robot[J].International Journal of Advanced Robotic Systems,2017,14(4):1-6.
[7]BUKHORI I,ISMAIL Z H.Detection strategy for kidnapped robot problem in Monte Carlo localization based on similarity measure of environment[C]∥IEEE International Conference on Underwater System Technology:Theory and Applications(USYS),IEEE,2016:55-60.
[8]路飞,田国会,刘国良,等.智能空间下基于WIFI指纹定位与粒子滤波的服务机器人复合全局定位系统设计[J].机器人,2016,38(2):178-184.
[9]CALONDER M,LEPETIT V,STRECHA C,et al.BRIEF:Binary robust independent elementary features[C]∥European Conference on Computer Vision,Springer-Verlag,2010:778-792.
[10]林汀,娄小平,刘锋,等.序列图像特征提取与匹配算法的改进[J].计算机工程与应用,2017,53(9):141-145.
[11]戴雪梅,郎朗,陈孟元.基于改进ORB的图像特征点匹配研究[J].电子测量与仪器学报,2016,30(2):233-240.
[12]JEON H K,JEONG J M,LEE K Y.An implementation of the realtime panoramic image stitching using ORB and PROSAC[C]∥SOC Design Conference,IEEE,2016:91-92.
[2]MAIR E,HAGER G D,BURSCHKA D,et al.Adaptive and generic corner detection based on the accelerated segment test[C]∥European Conference on Computer Vision,Springer,Berlin,Heidelberg,2010:183-196.
[3]RUBLEE E,RABAUD V,KONOLIGE K,et al.ORB:An efficient alternative to SIFT or SURF[C]∥IEEE International Conference on Computer Vision,IEEE,2012:2564-2571.
[4]MA L,LIN Y,CUI Y,et al.Vision-based positioning method based on landmark using multiple calibration lines[C]∥Proceedings of the 2016 International Conference on Communications,Signal Processing,and Systems,Springer,2017:471.
[5]FOX D,THRUN S,BURGARD W,et al.Particle filters for mobile robot localization[M].New York:Springer,2001:401-428.
[6]BUKHORI I,ISMAIL Z H.Detection of kidnapped robot problem in Monte Carlo localization based on the natural displacement of the robot[J].International Journal of Advanced Robotic Systems,2017,14(4):1-6.
[7]BUKHORI I,ISMAIL Z H.Detection strategy for kidnapped robot problem in Monte Carlo localization based on similarity measure of environment[C]∥IEEE International Conference on Underwater System Technology:Theory and Applications(USYS),IEEE,2016:55-60.
[8]路飞,田国会,刘国良,等.智能空间下基于WIFI指纹定位与粒子滤波的服务机器人复合全局定位系统设计[J].机器人,2016,38(2):178-184.
[9]CALONDER M,LEPETIT V,STRECHA C,et al.BRIEF:Binary robust independent elementary features[C]∥European Conference on Computer Vision,Springer-Verlag,2010:778-792.
[10]林汀,娄小平,刘锋,等.序列图像特征提取与匹配算法的改进[J].计算机工程与应用,2017,53(9):141-145.
[11]戴雪梅,郎朗,陈孟元.基于改进ORB的图像特征点匹配研究[J].电子测量与仪器学报,2016,30(2):233-240.
[12]JEON H K,JEONG J M,LEE K Y.An implementation of the realtime panoramic image stitching using ORB and PROSAC[C]∥SOC Design Conference,IEEE,2016:91-92.