徐伟杰, 李平, 韩波. 基于2点RANSAC的无人直升机单目视觉SLAM[J]. 机器人, 2012, 34(1): 65-71..
XU Weijie, LI Ping, HAN Bo. Monocular Visual SLAM of Unmanned Helicopter Based on 2-point RANSAC. ROBOT, 2012, 34(1): 65-71..
Abstract:The 1-point random sample consensus(RANSAC) algorithm is a data association algorithm with high accuracy and low compaction cost.However,it fails when angular velocities around multiple axes of the camera change quickly,and causes the risk of filter divergence when applied to the monocular visual simultaneous localization and mapping(SLAM) of unmanned helicopter.For this problem,2-point RANSAC algorithm is proposed,which incorporates a priori information from the EKF(extended Kalman filter) motion model,and uses RANSAC,in which only 2 matched points are used for sampling,to remove the outliers.Monocular visual SLAM based on 2-point RANSAC algorithm is performed on a mini unmanned helicopter(MUH) platform.The field-experiment results show that 2-point RANSAC algorithm works reliably, and the SLAM's pose estimation is precise enough for autonomous flight.
[1] Shakernia O,Vidal R,Sharp C S,et al.Multiple view motion estimation and control for landing an unmanned aerial vehicle[C]//IEEE International Conference on Robotics and Automation.Piscataway,NJ,USA:IEEE,2002:2793-2798.
[2] Sharp C S,Shakernia O,Sastry S S.A vision system for landing an unmanned aerial vehicle[C]//IEEE International Conference on Robotics and Automation.Piscataway,NJ,USA:IEEE,2001:1720-1727.
[3] Sasa S,Gobi H,Nonomiya T,et al.Position and attitude estimation using image proceeding of runway[C]//Proceedings of 38th Aerospace Sciences Meeting and Exhibition.Reston,VA,USA:AIAA,2000:1-10.
[4] Miller A,Shah M,Harper D.Landing a UAV on a runway using image registration[C]//IEEE International Conference on Robotics and Automation.Piscataway,NJ,USA:IEEE,2008:182-187.
[5] Martínez C,Mondrag6n I F,Olivares-Méndez M A,et al.Onboard and ground visual pose estimation techniques for UAV control[J].Journal of Intelligent and Robotic Systems,2011,61(1-4):301-320.
[6] 任沁源,李平,韩波.基于视觉信息的微型无人直升机位姿估计[J].浙江大学学报:工学版,2009,43(1):18-22.Ren Q Y,Li P,Han B.Vision-based mini unmanned helicopter pose and position estimation[J].Journal of Zhejiang University:Engineering Science,2009,43(1):18-22.
[7] Kim J,Sukkarieh S.Real-time implementation of airborne inertial-SLAM[J].Robotics and Autonomous Systems,2007,55(1):62-71.
[8] Aouf N,Sazdovski V,Tsourdos A,et al.Low altitude airborne SLAM with INS aided vision system[C]//Proceedings of AIAA Guidance,Navigation and Control Conference.Reston,VA,USA:AIAA,2007.
[9] Sinderhauf N,Lange S,Protzel P.Using the unscented Kalman filter in mono-SLAM with inverse depth parameterization for autonomous airship control[C]//IEEE International Workshop on Safety,Security and Rescue Robotics.Piscataway,NJ,USA:IEEE,2007:1-6.
[10] Colombatti G,Aboudan A,La Gloria N,et al.Lighter-than-air UAV with SLAM capabilities for mapping applications and atmosphere analyses[J].Memorie della Societa Astronomica Italiana Supplement,2011,16:42-49.
[11] Langelaan J,Rock S.Towards autonomous UAV flight in forests[C]//Proceedings of AIAA Guidance,Navigation and Control Conference.Reston,VA,USA:AIAA,2005:1-13.
[12] Caballero F,Merino L,Ferruz J,et al.Vision-based odometry and SLAM for medium and high altitude flying UAVs[J].Journal of Intelligent and Robotic Systems,2009,54(1-3):137-161.
[13] Artieda J,Sebastian J M,Campoy P,et al.Visual 3-D SLAM from UAVs[J].Journal of Intelligent and Robotic Systems,2009,55(4/5):299-321.
[14] Dissanayake M W M G,Newman P,Clark S,et al.A solution to the simultaneous localization and map building(SLAM)problem[J].IEEE Transactions on Robotics and Automation,200l,17(3):229-241.
[15] Civera J,Davison A J,Montiel J.Inverse depth parametrization for monocular SLAM[J].IEEE Transactions on Robotics,2008,24(5):932-945.
[16] Davison A J.Real-time simultaneous localization and mapping with a single camera[C]//Proceedings of International Conference on Computer Vision.Piscataway,NJ,USA:IEEE,2003:1403-1410.
[17] Davison A J,Reid I,Molton N,et al.MonoSLAM:Real-time single camera SLAM[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2007,29(6):1052-1067.
[18] Bailey T.Mobile Robot localisation and mapping in extensive outdoor environments[D].Sydney,Australia:Sydney University,2002.
[19] Neira J,Tard6s J D.Data association in stochastic mapping using the joint compatibility test[J].IEEE Transactions on Robotics and Automation,2001,17(6):890-897.
[20] Davey S J.Simultaneous localization and map building using the probabilistic multi-hypothesis tracker[J].IEEE Transactions on Robotics,2007,23(2):271-280.
[21] Civera J,Grasa O G,Davison A J.1-Point RANSAC for extended Kalman filtering:Application to real-time structure from motion and visual odometry[J].Journal of Field Robotics,2010,27(5):609-631.
[22] Martinez-Cantin R,Castellanos J A.Bounding uncertainty in EKF-SLAM:The robocentric local approach[C]//IEEE International Conference on Robotics and Automation.Piscataway,NJ,USA:IEEE,2006:430-435.
[23] Bailey T.Constrained initialisation for bearing-only SLAM[C]//IEEE International Conference on Robotics and Automation.Piscataway,NJ,USA:IEEE,2003:1966-1971.
[24] Solà J,Monin A,Devy M,et al.Undelayed initialization in bearing only SLAM[C]//IEEE/RSJ International Conference on Intelligent Robots and Systems.Piscataway,NJ,USA:IEEE,2005:2499-2504.