Page 68 - 《软件学报》2020年第9期

张亮 等:扫地机器人增强位姿融合的 Cartographer 算法及系统实现 2689

Table 3 Match scores with or without odometer data processing collision
表 3 有无里程计数据处理发生碰撞的匹配分数
Min Max Mean
有里程计数据处理 0.651 0.867 0.723
无里程计数据处理 0.650 0.698 0.676

4 总 结
本文主要对当前的激光 SLAM 算法进行了分析和研究,在 Cartographer 的基础上设计了基于位姿增量的多
传感器位姿融合算法,在 Player 平台设计实现了基于增强 Cartographer 算法的 SLAM 系统,并在实际场景生成
2D 栅格地图.

5 展 望

提高扫地机器人智能化,是未来服务机器人应用的一个重要方向,之后的研究还可以从以下几个方面进
行.(1) 目前使用的传感器无法探测语义信息 [27] ,从而限制机器人的智能化.将来可以研究加入视觉传感器,在提
供更精确位姿的同时,能够与深度学习结合,在不同场景使用不同的清扫方式,增强机器人的智能化程度;(2) 目
前,在扫地机器人上实现的是二维环境下的 SLAM 算法,在今后的实际发展中,三维环境的 SLAM 算法具有更广
泛的应用场景;(3)究在复杂场景对动态物体的检测以及进行轨迹的预测,实现规避,让机器人更安全、更方便.

References:
[1] Leonard JJ, Durrant-Whyte HF. Mobile robot localization by tracking geometric beacons. IEEE Robotics and Automation, 1991,
7(3):376−382.
[2] Liang Z, Peiyi S, Guangming Z, et al. A fast robot identification and mapping algorithm based on kinect sensor. Sensors, 2015,
15(8):19937−19967.
[3] Zhang L, Shen P, Ding J, et al. An improved RGB-D SLAM algorithm based on Kinect sensor. In: Proc. of the IEEE Int’l Conf. on
Advanced Intelligent Mechatronics. IEEE, 2015.
[4] Nister D, Narodisky O, Bergen J. Visual odometry for ground vehicle applications. Journal of Field Robotics, 2006,23(1):3−20.
[5] Alin A, Butz MV. Improved tracking and behavior anticipation by combining street map information with bayesian-filtering. In:
Proc. of the Int’l IEEE Conf. on Intelligent Transportation Systems. IEEE, 2014.
[6] Grisetti G, KuMmerle R, Stachniss C, et al. A tutorial on graph-based SLAM. Intelligent Transportation Systems Magazine IEEE,
2010,2(4):31−43.
[7] Ho KL, Newman P. Loop closure detection in SLAM by combining visual and spatial appearance. Robotics and Autonomous
Systems, 2006,54(9):740−749.
[8] Hess W, Kohler D, Rapp H, et al. Real-time loop closure in 2D LIDAR SLAM. In: Proc. of the 2016 IEEE Int’l Conf. on Robotics
and Automation (ICRA). IEEE, 2016.
[9] Isbell JR. Six theorems about injective metric spaces. Commentarii Mathematici Helvetici, 1964,39:65−76. [doi: 10.1007/
BF02566944]
[10] Lee YC, Yu W, Lim JH, et al. Sonar grid map based localization for autonomous mobile robots. In: Proc. of the 2008 IEEE/ASME
Int’l Conf. on Mechtronic and Embedded Systems and Applicationbs. 2008. 558−563.
[11] Lu F, Milios E. Globally consistent range scan alignment for environment mapping. Autonomous Robots, 1997,4(4):333−349.
[12] Martín F, Triebel R, Moreno L, Siegwart R. Two different tools for three-dimensional mapping: DE-based scan matching and
feature-based loop detection. Robotica, 2014,32(1):19−41.
[13] Agarwal S, Mierle K, et al. Ceres solver. http://ceres-solver.org
[14] Julier S, Uhlmann JK. A new extension of the Kalman filter to nonlinear systems. In: Proc. of the Int’l Symp. on
Aerospace/Defense Sensing, Simul. and Controls. Signal Processing, Sensor Fusion, and Target Recognition VI. 3. 1997. 182.
[15] Konolige K, Grisetti G, Kümmerle R, et al. Sparse pose adjustment for 2D mapping. In: Proc. of the IROS. 2010.
[16] Land AH, Doig AG. An automatic method of solving discrete programming problems. Econometrica, 1960,28(3):497−520.