WANG Ming-yi, HE Li-le, LI Yu, SUO Chao
（College of Mechanical & Electrical Engineering, Xi’an University of Architecture & Technology, Xi’an 710055, China）
Abstract： In order to effectively reduce the uncertainty error of mobile robot localization with a single sensor and improve the accuracy and robustness of robot localization and mapping, a mobile robot localization algorithm based on multi-sensor information fusion (MSIF) was proposed. In this paper, simultaneous localization and mapping (SLAM) was realized on the basis of laser Rao-Blackwellized particle filter (RBPF)-SLAM algorithm and graph-based optimization theory was used to constrain and optimize the pose estimation results of Monte Carlo localization. The feature point extraction and quadrilateral closed loop matching algorithm based on oriented FAST and rotated BRIEF (ORB) were improved aiming at the problems of generous calculation and low tracking accuracy in visual information processing by means of the three-dimensional (3D) point feature in binocular visual reconstruction environment. Factor graph model was used for the information fusion under the maximum posterior probability criterion for laser RBPF-SLAM localization and binocular visual localization. The results of simulation and experiment indicate that localization accuracy of the above-mentioned method is higher than that of traditional RBPF-SLAM algorithm and general improved algorithms, and the effectiveness and usefulness of the proposed method are verified.
Key words： mobile robot; simultaneous localization and mapping (SLAM); graph-based optimization; sensor fusion
CLD number： TP242.6 doi： 10.3969/j.issn.1674-8042.2020.02.007
References
［1］Doucet A, De Freitas N, Murphy K, et al. Rao-blackwellised particle filtering for dynamic Bayesian networks. In: Proceedings of Sixteenth Conference on Uncertainty in Artificial Intelligence, San Francisco, 2000: 176-183.
［2］Zhang Y, Zheng X F, Luo Y, et al. SLAM algorithm of Rao-Blackwellized particle filter based on resampling of Gaussian distribution. Control and Decision, 2016, 31(12): 2299-2304.
［3］Luo Y, Fu L, Cheng T F. Simultaneous localization and map construction based on improved Rao-Blackwellized particle filter. Control Theory and Application, 2015, 32(2): 267-272.
［4］Wang X W, He L L, Zhao T. Mobile robot for SLAM research based on lidar and binocular vision fusion. Chinese Journal of Sensors and Actuators, 2018, 31(3): 394-399.
［5］Wu Y J, Chen Y D, Chen M Y. Research on RBPF-SLAM algorithm under quantum particle swarm optimization. Journal of Intelligent Systems, 2018, (5): 829-835.
［6］Klein G, Murray D. Parallel tracking and mapping for small AR workspaces. In: Proceedings of 6th IEEE and ACM International Symposium on Mixed and Augmented Reality, 2007.
［7］Mur-Artal R, Montiel J M M, Tardos J D. ORB-SLAM: a versatile and accurate monocular SLAM system. IEEE Transactions on Robotics, 2015, 31(5): 1147-1163.
［8］Mur-Artal R, Tardos J D. ORB-SLAM2: an open-source SLAM system for monocular, stereo, and RGB-D cameras. IEEE Transactions on Robotics, 2017, 33(5): 1255-1262.
［9］Rublee E, Rabaud V, Konolige K, et al. ORB: an efficient alternative to SIFT or SURF. In: Proceedings of IEEE International Conference on Computer Vision, Barcelona, 2012: 2564-2571.
［10］Fan J J. Simultaneous localization and mapping based on binocular stereo vision under outdoor environment. Hefei: University of Science and Technology of China, 2016.
［11］Zhang Y, Du F Y, Luo Y, et al. A method of creating slam map integrating laser and depth vision sensor. Computer Application Research, 2016, 33(10): 2970-2972.
［12］Nelson E, Michael N, Dellaert F. An experimental study of robust distributed multi-robot data association from arbitrary poses. New York: Springer International Publishing, 2016.
［13］Forster C, Carlone L, Dellaert F, et al. On-manifold preintegration for real-time visual-inertial odometry. IEEE Transactions on Robotics, 2016, 33(1): 1-21.
［14］Burguera A, Gonzalez Y, Oliver G. The likelihood field approach to sonar scan matching. In: Proceedings of IEEE/RSJ International Conference on Intelligent Robots & Systems, 2008: 2977-2982.
［15］Liang M J, Min H Q, Luo R H. Summary of simultaneous localization and mapping based on graph optimization. Robot, 2013, 35(4): 500-512.
［16］Pomerleau F, Colas F, Siegwart R. A review of point cloud registration algorithms for mobile robotics. Foundations and Trends in Robotics, 2015, 4(1): 1-104.
［17］Karami E, Prasad S, Shehata M. Image matching using SIFT, SURF, BRIEF and ORB: performance comparison for distorted images. In: Proceedings of Newfoundland Electrical and Computer Engineering Conference, St. John’s, 2015.
［18］Fan J J, Liang H W, Zhu H, et al. Quadrilateral closed-loop tracking algorithm based on binocular vision. Robot, 2015, 37(6): 674-682.
［19］Schnabel R, Wahl R, Klein R. Efficient RANSAC for point-cloud shape detection. Computer Graphics Forum, 2010, 26(2): 214-226.
［20］Sibley G, Matthies L, Sukhatme G. Sliding window filter with application to planetary landing. Journal of Field Robotics, 2010, 27(5): 587-608.
［21］Kaess M, Johannsson H, Roberts R, et al. iSAM2: incremental smoothing and mapping using the Bayes tree. International Journal of Robotics Research, 2012, 31(2): 216-235.
多传感器信息融合的移动机器人定位算法研究
王铭艺， 贺利乐， 李 育， 索 超
（西安建筑科技大学 机电工程学院， 陕西 西安 710055）
摘 要： 为有效降低使用单一传感器进行移动机器人定位时的不确定误差， 提高机器人定位与建图的准确性和鲁棒性， 提出了一种多传感器信息融合的移动机器人定位算法。 基于激光RBPF-SLAM算法实现机器人同时定位与路标地图构建， 运用图优化理论约束优化蒙特卡洛定位的位姿估计结果； 通过双目视觉重建环境的三维点特征， 针对视觉信息处理计算量大、 跟踪精度不高的问题， 研究改进基于ORB的特征点提取与四边形闭环匹配算法； 利用因子图模型对激光RBPF-SLAM定位和双目视觉定位进行最大后验概率准则下的信息融合。 仿真和实验结果表明通过上述方法可以得到比传统RBPF-SLAM算法及一般改进算法更高的定位精度， 验证了所提方法的有效性和实用性。
关键词: 移动机器人； 同时定位与建图； 图优化； 传感器融合
引用格式： WANG Ming-yi, HE Li-le, LI Yu, et al. Mobile robot localization algorithm based on multi-sensor information fusion. Journal of Measurement Science and Instrumentation, 2020, 11（2）： 152-160. ［doi： 10.3969／j.issn.1674-8042.2020.02.007］
[full text view]
