Obstacle Recognition and Traversability Analysis of Tracked Vehicles in Off-road Environment

doi:10.12382/bgxb.2024.0981

Abstract

Abstract:

To address the limitations of existing traversability analysis methods,which often suffer from incomplete obstacle recognition and poor generalization in complex off-road environments,this paper proposes an obstacle recognition method based on open-vocabulary semantic segmentation.The method extracts the semantic labels of obstacles and terrain around the vehicle,enabling effective identification of previously unseen obstacles in unstructured environments.The method is validated on the datasets in real-world experiments,demonstrating its stability and comprehensive recognition capability.On this basis,a multi-layer 2.5D map is constructed by integrating semantic labels with 3D point clouds.The traversability level of a terrain is preliminarily classified according to semantic labels.And then the terrain smoothness is quantified based on ground elevation,and the geometric parameters of special environmental features (e.g.,vertical wall) are measured.Furthermore,the driving posture of vehicle is predicted by incorporating the geometric configuration of a tracked vehicle,thereby quantifying the coupling relationship among static slope stability,semantic terrain categories and geometric attributes.A cost function is then designed to jointly assess the traversal risk and cost of vehicle,ultimately generating a vehicle-centric traversability map.The effectiveness and reliability of the proposed method are verified by comparing it with similar methods,which enhances data support for decision-making,planning,and control of unmanned tracked platforms.

Key words: tracked vehicle, off-road environment, traversability analysis, elevation map, semantic segmentation

CLC Number:

TP391.4

WANG Haodong, MA Biao, CHEN Man, YU Liang, TAN Yunlu, LIU Yujian. Obstacle Recognition and Traversability Analysis of Tracked Vehicles in Off-road Environment[J]. Acta Armamentarii, 2025, 46(9): 240981-.

Figures/Tables 18

Fig.1 Schematic diagram of traversability analysis framework

Fig.2 Diagram of semantic information propagation from 2D images to 3D point clouds

Fig.3 Schematic diagram of semantic-based hierarchical layers

Table 1 Comparison between single frame point cloud and local map

t/s	单帧点云	局部地图
10.71
17.41
40.59
54.52

Fig.4 Construction results of elevation map

Fig.5 Roughness layer generation algorithm

Fig.6 Schematic diagram of convolution kernel and angle estimation method

Fig.7 Vertical wall layer generation algorithm

Fig.8 Experimental tracked vehicles and sensor layout

Table 2 Main parameters of the experimental platform

参数	数值
底盘尺寸/mm	1023×778×400
履带宽度/mm	150
接地段长度/mm	560
平台重量/kg	约140
最大纵向爬坡角/(°)	30
最大横向侧倾角/(°)	22
最大越障高度/mm	270

Table 3 Main parameters of using method

类别	指标
栅格尺寸	0.15m
地图长×宽	30×30m
最大离群值n_t	6
平整度归一化参数T_rough	0.6
代价函数加权系数φ₁、φ₂和φ₃	0.4、0.3、0.3

Table 4 Candidate class labels for open-vocabulary semantic segmentation method

级别	标签	代价分数
易通行	道路,人行道,草地,泥土	1.0
可通行	灌木,碎石,泥浆,水坑,沙地	0.6
不可通行	人,树,卡车,汽车,坦克,河流,湖泊,建筑物,天空	0.0

Table 5 Semantic segmentation results of RELLIS-3D dataset

场景	图像	真值标签	语义分割结果
道路
山丘

Fig.9 Semantic segmentation and construction of semantic layers

Fig.10 Construction results of roughness layer

Fig.11 Construction results of capacity constraint layer

Fig.12 Construction results of vertical wall layer

Table 6 Construction results and comparison of traversability layers

场景图像	本文方法	文献[17]方法	文献[24]方法

References 24

[1]	聂士达, 刘辉, 廖志昊, 等. 考虑复杂地形的越野环境无人车辆路径规划研究[J]. 机械工程学报, 2024, 60(10):261-272.
	NIE S D, LIU H, LIAO Z H, et al. Research on path planning of unmanned vehicles in off-road environments considering complex terrain[J]. Journal of Mechanical Engineering, 2024, 60(10):261-272. (in Chinese)
[2]	王建涛, 杨超, 刘帅帅, 等. 考虑系统噪声与载重未知的智能车路况辨识[J/OL]. 中国机械工程, 2025(2024-11-25)[2025-08-21]. http://kns.cnki.net/kcms/detail/42.1294.TH.20241125.1317.002.html.
	WANG J T, YANG C, LIU S S, et al. Intelligent vehicle road condition identification considering system noise and unknown load[J/OL]. China Mechanical Engineering, 2025(2024-11-25) [2025-08-21]. http://kns.cnki.net/kcms/detail/42.1294.TH.20241125.1317.002.html. (in Chinese)
[3]	胡林, 杨冬兆, 张新, 等. 基于DQP-LMPC的智能车超车换道动态路径规划[J]. 机械工程学报, 2024, 60(10):171-181.
	HU L, YANG D Z, ZHANG X, et al. Dynamic Path Planning for Intelligent Vehicle Overtaking and Lane Changing Based on DQP-LMPC[J]. Journal of Mechanical Engineering, 2024, 60(10):171-181. (in Chinese)
[4]	张佳楠, 胡钊政, 孟杰, 等. 面向车-路-图协同的分布式自动驾驶仿真平台架构及应用[J]. 汽车工程, 2024, 46(8):1335-1345,1356.
	ZHANG J N, HU Z Z, MENG J, et al. Distributed autonomous driving simulation platform architecture and application oriented to vehicle-road-map collaboration[J]. Automotive Engineering, 2024, 46(8):1335-1345,1356. (in Chinese)
[5]	GASPARINO M V, SIVAKUMAR A N, CHOWDHARY G. WayFASTER:a self-supervised traversability prediction for increased navigation awareness:arXiv:2402.00683[R/OL]. Ithaca,NY, US: Cornell University, 2024(2024-03-09). https://arxiv.org/abs/2402.00683.
[6]	WANG K, WANG M, WANG R, et al. Traversability Estimation for Off-road Autonomous Driving under Ego-motion Uncertainty[J]. IEEE Sensors Journal, 2024, 24(5):6584-6596.
[7]	周梦如, 陈慧岩, 熊光明, 等. 越野环境下无人履带平台的道路可通行性分析[J]. 兵工学报, 2022, 43(10):2485-2496. doi: 10.12382/bgxb.2021.0824
	ZHOU M R, CHEN H Y, XIONG G M, et al. Road passability analysis of unmanned tracked platform in off-road environments[J]. Acta Armamentarii, 2022, 43(10):2485-2496. (in Chinese)
[8]	BEYCIMEN S, IGNATYEV D, ZOLOTAS A. A comprehensive survey of unmanned ground vehicle terrain traversability for unstructured environments and sensor technology insights[J]. Engineering Science and Technology,an International Journal, 2023, 47:101457.
[9]	GUAN T, KOTHANDARAMAN D, CHANDRA R, et al. GA-Nav:efficient terrain segmentation for robot navigation in unstructured outdoor environments[J]. IEEE Robotics and Automation Letters, 2022, 7(3):8138-8145.
[10]	MATURANA D, CHOU P W, UENOYAMA M, et al. Real-time semantic mapping for autonomous off-road navigation[C]//Proceedings of International Conference on Field and Service Robotics.Cham, Switzerland:Springer, 2018:335-350.
[11]	FREY J, MATTAMALA M, CHEBROLU N, et al. Fast traversability estimation for wild visual navigation[C]// Proceedings of Robotics: Science and System XIX.Daegu, South Korea: Robotics Science & Systems Foundation, 2023.
[12]	ERNI G, FREY J, MIKI T, et al. MEM:multi-modal elevation mapping for robotics and learning[C]//Proceedings of 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems.Detroit,MI, US:IEEE, 2023:11011-11018.
[13]	MATTAMALA M, FREY J, LIBERA P, et al. Wild visual navigation:fast traversability learning via pre-trained models and online self-supervision[J]. Autonomous Robots, 2025, 49:19.
[14]	OQUAB M, DARCET T, MOUTAKANNI T, et al. DINOv2:learning robust visual features without supervision:arXiv:2304.07193[R/OL]. Ithaca,NY, US: Cornell University, 2023(2024-02-02). https://arxiv.org/abs/2304.07193.
[15]	CHEN D L, ZHUANG M X, ZHONG X Y, et al. RSPMP:real-time semantic perception and motion planning for autonomous navigation of unmanned ground vehicle in off-road environments[J]. Applied Intelligence, 2023, 53(5):4979-4995.
[16]	LEUNG T H Y, IGNATYEV D, ZOLOTAS A. Hybrid terrain traversability analysis in off-road environments[C]// Proceedings of the 2022 8th International Conference on Automation,Robotics and Applications.Prague, Czech Republic: IEEE, 2022:50-56.
[17]	PAN Y Y, XU X C, DING X Q, et al. GEM:online globally consistent dense elevation mapping for unstructured terrain[J]. IEEE Transactions on Instrumentation and Measurement, 2021, 70:1-13.
[18]	LIU Z X, YUAN X F, HUANG G M, et al. 3D gradient reconstruction-based path planning method for autonomous vehicle with enhanced roll stability[J]. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(11):20563-20571.
[19]	陶俊峰, 刘海鸥, 关海杰, 等. 基于可通行度估计的无人履带车辆路径规划[J]. 兵工学报, 2023, 44(11):3320-3332. doi: 10.12382/bgxb.2023.0262
	TAO J F, LIU H O, GUAN H J, et al. Path Planning of Unmanned Tracked Vehicle Based on Passability Estimation[J]. Acta Armamentarii, 2023, 44(11):3320-3332. (in Chinese)
[20]	XU M D, ZHANG Z, WEI F Y, et al. SAN:side adapter network for open-vocabulary semantic segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 45(12):15546-15561.
[21]	RADFORD A, KIM J W, HALLACY C, et al. Learning transferable visual models from natural language supervision:arXiv:2103.00020[R/OL]. Ithaca,NY, US: Cornell University, 2021(2021-02-26). https://arxiv.org/abs/2103.00020.
[22]	SHAN T X, ENGLOT B, MEYERS D, et al. LIO-SAM:tightly-coupled lidar inertial odometry via smoothing and mapping[C]//Proceedings of 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems.Las Vegas,NV, US:IEEE, 2020:5135-5142.
[23]	WERMELINGER M, FANKHAUSER P, DIETHELM R, et al. Navigation planning for legged robots in challenging terrain[C]// Proceedings of 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems.Daejeon, South Korea: IEEE, 2016:1184-1189.
[24]	SHAN T X, WANG J K, ENGLOT B, et al. Bayesian generalized kernel inference for terrain traversability mapping[C]//Proceedings of the 2nd Conference on Robot Learning.Zürich, Switzerland:PMLR, 2018:829-838.