摘要
提出了一个主动视觉即时定位与地图构建(SLAM)系统,能够避开障碍物,预测行人运动方向并且躲避行人,同时能够在未知环境中获得有效路径和进行稀疏三维点云地图构建.该系统由机器人平台、RGB-D摄像机和双目摄像机构成.RGB-D摄像机基于RGB-D上半身探测器进行行人检测与跟踪,同时使用RGB-D摄像机进行三维地图构建.双目摄像机通过获取深度信息寻找可通行路径.该系统实现了主动地图构建并且避免了由传统方法构建的静态地图包含行人的情况.实验验证了该系统的有效性.
We present an active visual Simultaneous Localization and Mapping(SLAM)system which is capable of avoiding obstacles,predicting the direction of pedestrians and avoiding pedestrians.Simultaneously,SLAM can obtain effective paths and 3-D map in unknown environments.It consists of a robot platform,an RGB-D camera and a stereo camera.The RGB-D camera is used for3-D mapping and pedestrian detection as well as tracking by RGB-D upper-body detectors.The stereo camera finds a passable path by leveraging the depth information.The proposed system enables active mapping and avoids the typical situations,in which people will appear in maps.The effectiveness of the system is finally verified by real-world experiments.
引文
[1] RANFT B,STILLER C.The role of machine vision for intelligent vehicles[J].IEEE Transactions on Intelligent Vehicles,2016,1(1):8-19.
[2] ONITA D,VARTAN N,KADAR M,et al.Quality control in porcelain industry based on computer vision techniques[C]∥2018International Young Engineers Forum(YEFECE).Costa da Caparica:IEEE,2018:79-84.
[3] RODRIGUEZ-VAZQUEZ A,FERNANDEZ-BERNI J,LENERO-BARDALLO J A,et al.Cmos vision sensors:embedding computer vision at imaging front-ends[J].IEEE Circuits and Systems Magazine,2018,18(2):90-107.
[4] GHYAR B S,BIRAJDAR G K.Computer vision based approach to detect rice leaf diseases using texture and color descriptors[C]∥2017International Conference on Inventive Computing and Informatics(ICICI).Coimbatore:IEEE,2017:1074-1078.
[5] DURRANT-WHYTE H,BAILEY T.Simultaneous localization and mapping:partⅠ[J].IEEE Robotics Automation Magazine,2006,13(2):99-110.
[6] LEONARD J J,DURRANT-WHYTE H F.Simultaneous map building and localization for an autonomous mobile robot[C]∥IEEE/RSJ Int Workshop on Intelligent Robots and Systems.Osaka:IEEE,1991:1442-1447.
[7] CHAVES S M,KIM A,EUSTICE R M.Opportunistic samplingbased planning for active visual slam[C]∥2014IEEE/RSJ International Conference on Intelligent Robots and Systems.Chicago:IEEE,2014:3073-3080.
[8] BLAER P S,ALLEN P K.Data acquisition and view planning for 3-D modeling tasks[C]∥IEEE/RSJ International Conference on Intelligent Robots and Systems.San Diego:IEEE,2007:417-422.
[9] CHIN W P,NTAFOS S.Optimum watchman routes[J].Information Processing Letters,1988,28(1):39-44.
[10] OKADA Y,MIURA J.Exploration and observation planning for 3D indoor mapping[C]∥2015 IEEE/SICE International Symposium on System Integration(SII).Nagoya:IEEE,2015:599-604.
[11] RUNO L K,KITANOV A,MAUROVI I,et al.Fast active slam for accurate and complete coverage mapping of unknown environments[C]∥International Conference on Intelligent Autonomous Systemspadova.Berlin:Springer,2014:415-428.
[12] AKULOVI M,ILE A,PETROVI I.Exploration and mapping of unknown polygonal environments based on uncertain range data[J].Automatika,2011,52(2):118-131.
[13] BORRMANN D,NCHTER A,DJAKULOVI’C M,et al.The project thermalmapper-thermal 3D mapping of indoor environments for saving energy[J].Ifac Symposioum on Robotic Control,2012,45(22):31-38.
[14] YAMAUCHI B.A frontier-based approach for autonomous exploration[C]∥IEEE International Symposium on Computational Intelligence in Robotics and Automation.Monterey:IEEE,2002:146-151.
[15] MENG Z H,SUN H,QIN H L,et al.Intelligent robotic system for autonomous exploration and active slam in unknown environments[C]∥IEEE/SICE International Symposium on System Integration.Taipei:IEEE,2017:651-656.
[16] KIM A,EUSTICE R M.Perception-driven navigation:active visual slam for robotic area coverage[C]∥IEEE International Conference on Robotics and Automation.Karlsruhe:IEEE,2013:3196-3203.
[17] DARKO T,SALAKA E,OSMANKOVIC D,et al.Active slam-based algorithm for autonomous exploration with mobile robot[C]∥IEEE International Conference on Industrial Technology.Seville:IEEE,2015:74-79.
[18] MORENC A,MARCO A,CALVO H.Visual SLAM and obstacle avoidance in real time for mobile robots navigation[C]∥International Conference on Mechatronics,Electronics and Automotive Engineering.Cuernavaca:IEEE,2015:44-49.
[19] LIZUKA S,NAKAMURA T,SUZUKI S.Robot navigation in dynamic environment using Navigation function APF with SLAM[C]∥2014 10th FranceJapan/8th Europe-Asia Congress on Mecatronics.Tokyo:IEEE,2015:89-92.
[20] GOLDHAMMER M,KOHLER S,DOLL K,et al.Camera based pedestrian path prediction by means of polynomial least-squares approximation and multilayer perceptron neural networks[C]∥Sai Intelligent Systems Conference.London:IEEE,2016:390-399.
[21] ISHIGURO T,MIYAMOTO R.An efficient prediction scheme for pedestrian tracking with cascade particle filter and its implementation on Cell/B.E[C]∥International Symposium on Intelligent Signal Processing and Communication Systems.Kanazawa,IEEE,2010:29-32.
[22] QUIGLEY M,CONLEY K,GERKEY B P,et al.Ros:an open-source robot operating system[J].ICRA Workshop on Open Source Software,2009,3:5.
[23] JAFARI O H,MITZEL D,LEIBE B.Real-time rgbd based people detection and tracking for mobile robots and head-worncameras[C]∥IEEEInternational Conference on Robotics and Automation.Hong Kong:IEEE,2014:5636-5643.
[24] MUR-ARTAL R,TARDS J D.Orb-slam2:an opensource slam system for monocular,stereo,and RGB-D cameras[J].IEEE Transactions on Robotics,2017,33(5):1255-1262.
[25] STURM J,ENGELHARD N,ENDRES F,et al.A benchmark for the evaluation of RGB-D slam systems[C]∥IEEE/RSJ International Conference on Intelligent Robots and Systems.Vilamoura:IEEE,2012:573-580.