Similar articles

Abstract: We present a real-time monocular simultaneous localization and mapping (SLAM) system with a new distributed structure for multi-UAV collaboration tasks. The system is different from other general SLAM systems in two aspects: First, it does not aim to build a global map, but to estimate the latest relative position between nearby vehicles; Second, there is no centralized structure in the proposed system, and each vehicle owns an individual metric map and an ego-motion estimator to obtain the relative position between its own map and the neighboring vehicles’. To realize the above characteristics in real time, we demonstrate an innovative feature description and matching algorithm to avoid catastrophic expansion of feature point matching workload due to the increased number of UAVs. Based on the hash and principal component analysis, the matching time complexity of this algorithm can be reduced from O(log N) to O(1). To evaluate the performance, the algorithm is verified on the acknowledged multi-view stereo benchmark dataset, and excellent results are obtained. Finally, through the simulation and real flight experiments, this improved SLAM system with the proposed algorithm is validated.

具有快速匹配特征算法的多无人机协作系统

[1]Amidi O, Kanade T, Fujita K, 1999. A visual odometer for autonomous helicopter flight. Robot Auton Syst, 28(2):185-193.

[2]Andersen ED, Taylor CN, 2007. Improving MAV pose estimation using visual information. IEEE/RSJ Int Conf on Intelligent Robots and Systems, p.3745-3750.

[3]Bay H, Tuytelaars T, van Gool L, 2006. SURF: speeded up robust features. Proc 9^th European Conf on Computer Vision, p.404-417.

[4]Caballero F, Merino L, Ferruz J, et al., 2006. Improving vision-based planar motion estimation for unmanned aerial vehicles through online mosaicing. Proc IEEE Int Conf on Robotics and Automation, p.2860-2865.

[5]Caballero F, Merino L, Ferruz J, et al., 2007. Homography based Kalman filter for mosaic building. Applications to UAV position estimation. Proc IEEE Int Conf on Robotics and Automation, p.2004-2009.

[6]Caballero F, Merino L, Ferruz J, et al., 2009. Unmanned aerial vehicle localization based on monocular vision and online mosaicking. J Intell Robot Syst, 55(4-5):323-343.

[7]Campoy P, Correa JF, Mondragón I, et al., 2009. Computer vision onboard UAVs for civilian tasks. J Intell Robot Syst, 54(1-3):105-135.

[8]Cunningham A, Indelman V, Dellaert F, 2013. DDF-SAM 2.0: consistent distributed smoothing and mapping. Proc IEEE Int Conf on Robotics and Automation, p.5220-5227.

[9]Eberli D, Scaramuzza D, Weiss S, et al., 2011. Vision based position control for MAVs using one single circular landmark. J Intell Robot Syst, 61(1-4):495-512.

[10]Forster C, Lynen S, Kneip L, et al., 2013. Collaborative monocular SLAM with multiple micro aerial vehicles. IEEE/RSJ Int Conf on Intelligent Robots and Systems, p.3962-3970.

[11]Fox D, Burgard W, Kruppa H, et al., 2000. A probabilistic approach to collaborative multi-robot localization. Auton Robot, 8(3):325-344.

[12]Howard A, Sukhatme GS, Matarić MJ, 2006. Multirobot simultaneous localization and mapping using manifold representations. Proc IEEE, 94(7):1360-1369.

[13]Ke Y, Sukthankar R, 2004. PCA-SIFT: a more distinctive representation for local image descriptors. Proc IEEE Computer Society Conf on Computer Vision and Pattern Recognition, p.506-513.

[14]Li TC, Su JY, Liu W, et al., 2017. Approximate Gaussian conjugacy: parametric recursive filtering under nonlinearity, multimodality, uncertainty, and constraint, and beyond. Front Inform Technol Electron Eng, 18(12):1913-1939.

[15]Lowe DG, 2004. Distinctive image features from scale- invariant keypoints. Int J Comput Vis, 60(2):91-110.

[16]Masayoshi M, Chen A, Singh SPN, et al., 2017. Autonomous helicopter tracking and localization using a self-surveying camera array. In: Corke P, Sukkariah S (Eds.). Field and Service Robotics. Springer Tracts in Advanced Robotics. Springer, Berlin, Heidelberg, Germany.

[17]McDonald J, Kaess M, Cadena C, et al., 2011. 6-DOF multi- session visual SLAM using anchor nodes. European Conf on Mobile Robotics, p.69-76.

[18]Meingast M, Geyer C, Sastry S, 2004. Vision based terrain recovery for landing unmanned aerial vehicles. Proc IEEE Conf on Decision and Control, p.1670-1675.

[19]Moallem P, Razmjooy N, 2012. Optimal threshold computing in automatic image thresholding using adaptive particle swarm optimization. J Appl Res Technol, 10(5):703-712.

[20]Mondragón IF, Campoy P, Martinez C, et al., 2010a. Omnidirectional vision applied to unmanned aerial vehicles (UAVs) attitude and heading estimation. Robot Auton Syst, 58(6):809-819.

[21]Mondragón IF, Olivares-Méndez MA, Campoy P, et al., 2010b. Unmanned aerial vehicles UAVs attitude, height, motion estimation and control using visual systems. Auton Robot, 29(1):17-34.

[22]Montemerlo M, Thrun S, Koller D, et al., 2002. FastSLAM: a factored solution to the simultaneous localization and mapping problem. Proc 8^th National Conf on Artificial Intelligence, p.593-598.

[23]Montemerlo M, Thrun S, Roller D, et al., 2003. FastSLAM 2.0: an improved particle filtering algorithm for simultaneous localization and mapping that provably converges. Proc 18^th Int Joint Conf on Artificial Intelligence, p.1151-1156.

[24]Montiel JMM, Civera J, Davison AJ, 2006. Unified inverse depth parametrization for monocular SLAM. Robotics: Science and Systems II, p.81-88.

[25]Mourikis AI, Trawny N, Roumeliotis SI, et al., 2009. Vision- aided inertial navigation for spacecraft entry, descent, and landing. IEEE Trans Robot, 25(2):264-280.

[26]Mur-Artal R, Montiel JMM, Tardós JD, 2015. ORB-SLAM: a versatile and accurate monocular SLAM system. IEEE Trans Robot, 31(5):1147-1163.

[27]Ready BB, Taylor CN, 2007. Improving accuracy of MAV pose estimation using visual odometry. Proc American Control Conf, p.3721-3726.

[28]Ready BB, Taylor CN, 2009. Inertially aided visual odometry for miniature air vehicles in GPS-denied environments. J Intell Robot Syst, 55(2-3):203-221.

[29]Rocha R, Dias J, Carvalho A, 2005. Cooperative multi-robot systems: a study of vision-based 3-D mapping using information theory. Proc IEEE Int Conf on Robotics and Automation, p.384-389.

[30]Simo-Serra E, Trulls E, Ferraz L, et al., 2015. Discriminative learning of deep convolutional feature point descriptors. IEEE Int Conf on Computer Vision, p.118-126.

[31]Templeton T, Shim DH, Geyer C, et al., 2007. Autonomous vision-based landing and terrain mapping using an MPC-controlled unmanned rotorcraft. IEEE Int Conf on Robotics and Automation, p.1349-1356.

[32]Tsai R, Huang T, Zhu WL, 1982. Estimating three- dimensional motion parameters of a rigid planar patch, II: singular value decomposition. IEEE Trans Acoust Speech Signal Process, 30(4):525-534.

[33]Vidal-Calleja TA, Berger C, Solà J, et al., 2011. Large scale multiple robot visual mapping with heterogeneous landmarks in semi-structured terrain. Robot Auton Syst, 59(9):654-674.

[34]Yi KM, Trulls E, Lepetit V, et al., 2016. LIFT: learned invariant feature transform. Proc 14^th European Conf on Computer Vision, p.467-483.

[35]Zhang ZY, 1997. Parameter estimation techniques: a tutorial with application to conic fitting. Image Vis Comput, 15(1): 59-76.