Map Lightweight Processing and Staircase Area Classification Method for Indoor Navigation of Unmanned Ground Platforms

doi:10.12382/bgxb.2024.0483

Abstract

Abstract:

Constructing an environment map is a crucial prerequisite for navigation,and a comprehensive and detailed map can effectively assist in planning the optimal motion paths for unmanned ground platforms.To address the issues of data redundancy and difficulty in distinguishing the terrain structures in traditional map construction methods,a lightweight map processing and staircase area classification method for indoor navigation of unmanned ground platforms is proposed.The method first extracts the traversable area for unmanned platforms to reduce data redundancy and removes the outliers based on the distribution characteristics of stair surfaces.Subsequently,a map construction algorithm incorporating edge smoothing is used to generate multi-layer grid maps with clear boundaries,regular shapes,and distinct levels.Then,the stair environment features are extracted,and a Naive Bayes classification algorithm with Laplace smoothing is employed to distinguish and label the structures such as steps and turning platforms.The experimental results show that the maps generated by this method maintain high resolution while reducing the data volume by an order of magnitude compared to traditional point cloud maps,and the macro-precision rate of map classification reaches 91.3%.Compared with conventional methods,the proposed method can construct more lightweight multi-layer grid maps with terrain classification labels,providing safe and efficient navigation support for unmanned ground platforms.

Key words: map data processing, staircase, lightweight, map classification, unmanned ground platform

CLC Number:

TP242

MA Yuwei, WU Weichao, WANG Wei, NIU Ailin, GUO Zhiming, YANG Jianxin. Map Lightweight Processing and Staircase Area Classification Method for Indoor Navigation of Unmanned Ground Platforms[J]. Acta Armamentarii, 2025, 46(6): 240483-.

Figures/Tables 16

Fig.1 Map construction process

Fig.2 Distribution of environmental normal vectors

Fig.3 Extracted point cloud

Fig.4 Geometric parameters of horizontal regions and decision domain

Fig.5 Diagram of outlier removal

Fig.6 ε-P relationship graph for outlier filtering

Fig.7 Pseudocode for MGM algorithm

Fig.8 Schematic diagram of Smoothing function convolution

Fig.9 Illustration of the results of removing the ceiling operation

Fig.10 Ground edge grid map

Fig.11 The statistical results of ground edge grid map

Table 1 Confusion matrix for multi-class classification

真实类别	预测类别
真实类别	c₁	c₂	…	c_k
c₁	$∑ i = 1 V I (p i = c 1, r i = c 1)$	$∑ i = 1 V I (p i = c 2, r i = c 1)$	…	$∑ i = 1 V I (p i = c k, r i = c 1)$
c₂	$∑ i = 1 V I (p i = c 1, r i = c 2)$	$∑ i = 1 V I (p i = c 2, r i = c 2)$	…	$∑ i = 1 V I (p i = c k, r i = c 2)$
︙	︙	︙		︙
c_k	$∑ i = 1 V I (p i = c 1, r i = c k)$	$∑ i = 1 V I (p i = c 2, r i = c k)$	…	$∑ i = 1 V I (p i = c k, r i = c k)$

Table 1 Confusion matrix for multi-class classification

真实类别	预测类别
真实类别	c₁	c₂	…	c_k
c₁	$∑ i = 1 V I (p i = c 1, r i = c 1)$	$∑ i = 1 V I (p i = c 2, r i = c 1)$	…	$∑ i = 1 V I (p i = c k, r i = c 1)$
c₂	$∑ i = 1 V I (p i = c 1, r i = c 2)$	$∑ i = 1 V I (p i = c 2, r i = c 2)$	…	$∑ i = 1 V I (p i = c k, r i = c 2)$
︙	︙	︙		︙
c_k	$∑ i = 1 V I (p i = c 1, r i = c k)$	$∑ i = 1 V I (p i = c 2, r i = c k)$	…	$∑ i = 1 V I (p i = c k, r i = c k)$

Table 2 Classification result evaluation value

评价指标	评价值
P_M	0.913
R_M	0.837
F1_M	0.872

Fig.12 Experiment on constructing multi-layer grid map

Table 3 Comparison of parameters of different map models

地图模型	数据集	能否直接用于路径规划	占用存储空间	面向地面无人平台的可通行区域占比/%
点云	S3DIS	否	82111KB
点云	BIT3DIS	否	2263MB
体素	S3DIS	是	4691KB	33.5
体素	BIT3DIS	是	33.5MB	22.0
三维网格	S3DIS	是	7505KB	40.0
三维网格	BIT3DIS	是	47.1MB	39.9
八叉树	S3DIS	是	1519KB	33.6
八叉树	BIT3DIS	是	13.8MB	22.3
MGM	S3DIS	是	3028KB	99.2
MGM	BIT3DIS	是	25MB	96.4

Fig.13 Schematic diagram of path planning

References 26

[1]	田野, 陈宏巍, 王法胜, 等. 室内移动机器人的SLAM算法综述[J]. 计算机科学, 2021, 48(9):223-234.
	TIAN Y, CHEN H W, WANG F S, et al. Overview of SLAM algorithms for mobile robots[J]. Computer Science, 2021, 48(9):223-234. (in Chinese)
[2]	TAHERI H, XIA Z C. SLAM:definition and evolution[J]. Engineering Applications of Artificial Intelligence, 2021, 97:104032.
[3]	张福斌, 张炳烁, 杨玉帅. 基于单目/IMU/里程计融合的SLAM算法[J]. 兵工学报, 2022, 43(11):2810-2818.
	ZHANG F B, ZHANG B S, YANG Y S. SLAM algorithm based on monocular / IMU / odometer fusion[J]. Acta Armamentarii, 2022, 43 (11):2810-2818. (in Chinese)
[4]	张耀, 吴一全, 陈慧娴. 基于深度学习的视觉同时定位与建图研究进展[J]. 仪器仪表学报, 2023, 44(7):214-241.
	ZHANG Y, WU Y Q, CHEN H X. Research progress of visual simultaneous localization and mapping based on deep learning[J]. Chinese Journal of Scientific Instrument, 2023, 44(7):214-241. (in Chinese)
[5]	李娇娇, 孙红岩, 董雨, 等. 基于深度学习的3维点云处理综述[J]. 计算机研究与发展, 2022, 59(5):1160-1179.
	LI J J, SUN H Y, DONG Y, et al. Survey of 3-dimensional point cloud processing based on deep learning[J]. Journal of Computer Research and Development, 2022, 59(5):1160-1179. (in Chinese)
[6]	SHAN T, ENGLOT B, MEYERS D, et al. LIO-SAM:tightly-coupled lidar inertial odometry via smoothing and mapping[C]// Proceedings of the 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).Las Vegas,NV,US:IEEE, 2020:5135-5142.
[7]	杨阳. 基于多线激光雷达的地图构建技术研究[J]. 计算机科学与应, 2022, 12(10):2249-2258.
	YANG Y. Research on map construction technology based on multi-line LiDAR[J]. Computer Science and Application, 2022, 12(10):2249-2258. (in Chinese)
[8]	HUANG J, RONI Y, VASSILY F, et al. An accurate method for voxelizing polygon meshes[C]// Proceedings of the IEEE Symposium on Volume Visualization (Cat.No.989EX300).Research Triangle Park,NC,US:IEEE, 1998:119-126.
[9]	MUGLIKAR M, ZHANG Z, SCARAMUZZA D. Voxel map for visual SLAM[C]// Proceedings of the 2020 IEEE International Conference on Robotics and Automation (ICRA).Paris,France:IEEE, 2020:4181-4187.
[10]	PUTZ S, WIEMANN T, SPRICKERHOF J, et al. 3D navigation mesh generation for path planning in uneven terrain[J]. IFAC Papers Online, 2016, 49(15):212-217.
[11]	张韵, 王淑营, 郑庆, 等. 保持细节几何特征的三维网格模型轻量化算法[J]. 计算机应用, 2023, 43(4):1226-1232
	ZHANG Y, WANG S Y, ZHENG Q, et al. Lightweight algorithm of 3D mesh model for preserving detailed geometric features[J]. Journal of Computer Applications, 2023, 43(4):1226-1232 (in Chinese)
[12]	RUETZ F, HERNANDEZ E, PFEIFFER M, et al. OVPC mesh:3D free-space representation for local ground vehicle navigation[C]// Canada:IEEE, 2019:8648-8654.
[13]	SAARINEN J P, ANDREASSON H, STOYANOV T, et al. 3D normal distributions transform occupancy maps:an efficient representation for mapping in dynamic environments[J]. International Journal of Robotics Research, 2013, 32(14):1627-1644.
[14]	VESPA E, NIKOLOV N, GRIMM M, et al. Efficient Octree-based volumetric SLAM supporting signed distance and occupancy mapping[J]. IEEE Robotics and Automation Letters, 2018, 3(2):1144-1151.
[15]	BATINOVIC A, PETROVIC T, IVANOVIC A, et al. A multi-resolution frontier-based planner for autonomous 3D exploration[J]. IEEE Robotics and Automation Letters, 2021, 6(3):4528-4535.
[16]	赵艺博, 霍冬浩, 陈彦钦, 等. 基于单目视觉的四轴飞行器体素地图重建系统的研究[J]. 电子技术与软件工程, 2022(9):172-175.
	ZHAO Y B, HUO D H, CHEN Y Q, et al. Research on voxel map reconstruction system for quadrotors based on monocular vision[J]. Electronic Technology & Software Engineering, 2022(9):172-175. (in Chinese)
[17]	蔡志宏, 赵慧, 周亮, 等. 一种多线激光雷达室外小范围导航算法设计[J]. 机械设计与制造, 2022, 374(4):258-261.
	CAI Z H, ZHAO H, ZHOU L, et al. Outdoor navigation research based on multi-line lidar[J]. Machinery Design & Manufacture, 2022, 374(4):258-261. (in Chinese)
[18]	STRICKER R, MULLER S, EINHORN E, et al. Interactive mobile robots guiding visitors in a university building[C]// Proceedings of the 21th Robot and Human Interactive Communication.Paris,France:IEEE, 2012:695-700.
[19]	KONOLIGE K, MARDER E, MARTHI B, et al. Navigation in hybrid metric-topological maps[C]// Proceedings of the 2011 IEEE International Conference on Robotics and Automation.Shanghai,China:IEEE, 2011:3041-3047.
[20]	THRUN S. Learning metric-topological maps for indoor mobile robot navigation[J]. Artificial Intelligence, 2017, 99(1):21-71.
[21]	熊光明, 于全富, 胡秀中, 等. 考虑平台特性的多层建筑物内履带式无人平台运动规划[J]. 兵工学报, 2023, 44 (3):841-850.
	XIONG G M, YU Q F, HU X Z, et al. A motion planner for unmanned tracked vehicles in multi-storey buildings considering the characteristics of Vehicles[J]. Acta Armamentarii, 2023, 44(3):841-850. (in Chinese)
[22]	张萸, 吕品, 赖际舟, 等. 基于激光雷达的多层楼梯检测和建模方法[J]. 导航定位与授时, 2024, 11(4):94-106.
	ZHANG Y, LU P, LAI J Z, et al. Multi-story staircase detection and modeling method based on LiDAR[J]. Navigation Positioning and Timing, 2024, 11(4):94-106. (in Chinese)
[23]	CAFARO B, GIANNI M, PIRRI F, et al. Terrain traversability in rescue environments[C]// Proceedings of the 2013 IEEE International Symposium on Safety,Security,and Rescue Robotics.Linkoping,Sweden:IEEE, 2013:1-8
[24]	虎玲, 常霞, 纪峰. 图像边缘检测方法研究新进展[J]. 现代电子技术. 2018, 41(23):32-37.
	HU L, CHANG X, JI F. New research progress of image edge detection methods[J]. Modern Electronics Technique, 2018, 41(23):32-37. (in Chinese)
[25]	肖扬, 周军. 图像边缘检测综述[J]. 计算机工程与应用, 2023, 59(5):40-54.
	XIAO Y, ZHOU J. Overview of image edge detection[J]. Computer Engineering and Applications, 2023, 59(5):40-54. (in Chinese)
[26]	IEO A, OZAN S, AMIR R, et al. 3D semantic parsing of large-scale indoor spaces[C]// Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition.Las Vegas,NV,US:IEEE, 2016:1534-1543.