An RGB-D SLAM Algorithm for Robot Based on the Improved Geometric andMotion Constraints in Dynamic Environment
AI Qinglin, LIU Gangjiang, XU Qiaoning
Key Laboratory of Special Purpose Equipment and Advanced Manufacturing Technology, Ministry of Education & Zhejiang Province, Zhejiang University of Technology, Hangzhou 310023, China
艾青林, 刘刚江, 徐巧宁. 动态环境下基于改进几何与运动约束的机器人RGB-D SLAM算法[J]. 机器人, 2021, 43(2): 167-176.DOI: 10.13973/j.cnki.robot.200147.
AI Qinglin, LIU Gangjiang, XU Qiaoning. An RGB-D SLAM Algorithm for Robot Based on the Improved Geometric andMotion Constraints in Dynamic Environment. ROBOT, 2021, 43(2): 167-176. DOI: 10.13973/j.cnki.robot.200147.
Abstract：The pose estimation accuracy and robustness of the indoor robot using traditional visual SLAM (simultaneous localization and mapping) systems in dynamic environments are poor because the moving feature points are incorrectly incorporated into the camera pose calculation. In order to solve this problem, the feature points are divided into 5 categories, including static feature points, unknown feature points, suspected static feature points, dynamic feature points, and mismatched feature points. Static feature points are screened with strict geometric constraints. Unknown feature points are divided into suspected static feature points, dynamic feature points, and mismatched feature points using multi-frame observation information, and Kalman filtering is performed. Finally, the static feature points, suspected static feature points, and dynamic feature points are all used for pose optimization. The experiments on the TUM dataset in indoor environments with moving objects show that the overall performance (including accuracy, robustness, and running speed) of the proposed algorithm is superior to other dynamic SLAM algorithms.
[1] Huang A S, Bachrach A, Henry P, et al. Visual odometry and mapping for autonomous flight using an RGB-D camera[M]//Robotics Research. Cham, Switzerland: Springer, 2017: 235-252. [2] Häne C, Heng L, Lee G H, et al. 3D visual perception for self-driving cars using a multi-camera system: Calibration, mapping, localization, and obstacle detection[J]. Image and Vision Computing, 2017, 68(S1): 14-27. [3] Schöps T, Engel J, Cremers D. Semi-dense visual odometry for AR on a smartphone[C]//IEEE International Symposium on Mixed and Augmented Reality. Piscataway, USA: IEEE, 2014: 145-150. [4] Fischler M A, Bolles R C. Random sample consensus: A paradigm for model-fitting with applications to image-analysis and automated cartography[J]. Communications of the ACM, 1981, 24(6): 381-395. [5] 高成强，张云洲，王晓哲，等．面向室内动态环境的半直接法 RGB-D SLAM 算法[J]．机器人，2019，41(3)：372-383.Gao C Q, Zhang Y Z, Wang X Z, et al. Semi-direct RGB-D SLAM algorithm for dynamic indoor environments[J]. Robot, 2019, 41(3): 372-383. [6] Zhong F W, Wang S, Zhang Z Q, et al. Detect-SLAM: Making object detection and SLAM mutually beneficial[C]//IEEE Winter Conference on Applications of Computer Vision. Piscataway, USA: IEEE, 2018: 1001-1010. [7] Sabzevari R, Scaramuzza D. Multi-body motion estimation from monocular vehicle-mounted cameras[J]. IEEE Transactions on Robotics, 2016, 32(3): 638-651. [8] 张慧娟，方灶军，杨桂林．动态环境下基于线特征的 RGB-D 视觉里程计[J]．机器人，2019，41(1)：77-84.Zhang H J, Fang Z J, Yang G L. RGB-D visual odometry in dynamic environments using line features[J]. Robot, 2019, 41(1): 77-84. [9] Alcantarilla P F, Yebes J J, Almazán J, et al. On combining visual SLAM and dense scene flow to increase the robustness of localization and mapping in dynamic environments[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA: IEEE, 2012: 1290-1297. [10] 林志林，张国良，姚二亮，等．动态场景下基于运动物体检测的立体视觉里程计[J]．光学学报，2017，37(11)：187-195.Lin Z L, Zhang G L, Yao E L, et al. Stereo visual odometry based on motion object detection in the dynamic scene[J]. Acta Optica Sinica, 2017, 37(11): 187-195. [11] Mur-Artal R, Tardós J D. ORB-SLAM2: An open-source SLAM system for monocular, stereo, and RGB-D cameras[J]. IEEE Transactions on Robotics, 2017, 33(5): 1255-1262. [12] Rublee E, Rabaud V, Konolige K, et al. ORB: An efficient alternative to SIFT or SURF[C]//International Conference on Computer Vision. Piscataway, USA: IEEE, 2011. DOI: 10.1109/ICCV.2011.6126544. [13] Fisher R A, Yates F. Statistical tables for biological, agricultural and medical research[M]. London, UK: Oliver and Boyd Ltd, 1943. [14] Zennaro S, Munaro M, Milani S, et al. Performance evalua-tion of the 1st and 2nd generation Kinect for multimedia applications[C]//IEEE International Conference on Multimedia and Expo. Piscataway, USA: IEEE, 2015. DOI: 10.1109/ICME. 2015.7177380. [15] Sturm J, Engelhard N, Endres F, et al. A benchmark for the eva-luation of RGB-D SLAM systems[C]//IEEE/RSJ International Conference on Intelligent Robots and Systems. Piscataway, USA: IEEE, 2012: 573-580. [16] Sun Y X, Liu M, Meng M Q H. Improving RGB-D SLAM in dynamic environments: A motion removal approach[J]. Robotics and Autonomous Systems, 2017, 89: 110-122. [17] Li S, Lee D. RGB-D SLAM in dynamic environments using static point weighting[J]. IEEE Robotics and Automation Letters, 2017, 2(4): 2263-2270.
