A Data-driven Method for Traversability Analysis and Dataset Generation on Extraterrestrial Terrain

ZHANG Zhiyu; ZHU Chang'an; TANG Min; TONG Ruofeng

doi:10.13203/j.whugis20210308

Volume 46 Issue 9

Sep. 2021

Turn off MathJax

Article Contents

Abstract

References

Geomatics and Information Science of Wuhan University > 2021 > 46(9): 1362-1369,1385. > DOI: 10.13203/j.whugis20210308

ZHANG Zhiyu, ZHU Chang'an, TANG Min, TONG Ruofeng. A Data-driven Method for Traversability Analysis and Dataset Generation on Extraterrestrial Terrain[J]. Geomatics and Information Science of Wuhan University, 2021, 46(9): 1362-1369,1385. DOI: 10.13203/j.whugis20210308

Citation:

PDF (2539 KB)

A Data-driven Method for Traversability Analysis and Dataset Generation on Extraterrestrial Terrain

1.
College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China

Funds:

The National Key Reaearch and Development Program of China 2018AAA0102703

the National Natural Science Foundation of China 61972341

the National Natural Science Foundation of China 61832016

the National Natural Science Foundation of China 51775496

the National Natural Science Foundation of China 61732015

More Information

Author Bio:
ZHANG Zhiyu, postgraduate, specializes in computer aided design and computer graphics. E-mail: 541600517@qq.com
Corresponding author:
TANG Min, PhD, professor. E?mail: tang_m@zju.edu.cn
Received Date: May 30, 2021
Published Date: September 17, 2021

Graphical Abstract

Abstract

Abstract

Objectives Traversability analysis is one of the necessary parts for rovers on extraterrestrial surface to explore unknown environment.
Methods In this paper, we propose a data-driven method for traversability analysis for rovers on extraterrestrial surface. Based on the inputting multi-dimensional terrain information, the proposed method models traversability analysis as a semantic segmentation problem, which can explicitly compute a traversability map of this circumstances for a specific rover. Meanwhile, we provide an algorithm for generating training dataset for the rover. We first run the rover in the field to collect directed traversability results at certain positions, and then fulfill the undirected traversability map with these results by converting this problem into a global optimization problem, since undirected traversability map is more intuitive and straightforward for path planning. We can get the dataset for a specific rover by linking this map with the data of environment. In order to get the data more efficiently, we design an algorithm to generate virtual extraterrestrial terrains randomly and to simulate the running of a specific rover.
Results We generate a set of visible multi-dimensional terrain information and perform traversing test in virtual environment, which is used for generating traversibility labels in the optimization method. Based on the terrain information and labels, we train a U-Net-like network for predicting labels according to the given multi-dimensional information, and the network performs well on test dataset with the accuracy of 93.8% on average.
Conclusions The proposed data⁃driven method for traversability analysis is effective in virtual environment.
- extraterrestrial terrain,
- multi-source map merging,
- traversability analysis,
- procedural content generation

FullText(HTML)

References (30)

References

[1]	Huertas A, Matthies L, Rankin A. Stereo-Based Tree Traversability Analysis for Autonomous OffRoad Navigation[C]//2005 Seventh IEEE Workshops on Applications of Computer Vision(WACV/ MOTION'05), Breckenridge, CO, USA, 2005
[2]	Kim D, Sun J, Oh S M, et al. Traversability Classification Using Unsupervised On-Line Visual Learning for Outdoor Robot Navigation[C]//IEEE International Conference on Robotics and Automation, Orlando, FL, USA, 2006
[3]	Zhang K, Niroui F, Ficocelli M, et al. Robot Navigation of Environments with Unknown Rough Terrain Using Deep Reinforcement Learning[C]//IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR), Philadelphia, PA, USA, 2018
[4]	Zhang Y F, Wang W S, Bonatti R, et al. Integrating Kinematics and Environment Context into Deep Inverse Reinforcement Learning for Predicting OffRoad Vehicle Trajectories[EB/OL]. [2021-03-11]. https://arxiv.org/pdf/1810.07225
[5]	Guastella D C, Muscato G. Learning-Based Methods of Perception and Navigation for Ground Vehicles in Unstructured Environments: A Review[J]. Sensors, 2020, 21(1): 73 doi: 10.3390/s21010073
[6]	李修贤, 孙敏, 黎晓东, 等. 面向空地协同应急的地表可通行性分析方法[J]. 石河子大学学报(自然科学版), 2019, 37(1): 12-20 https://www.cnki.com.cn/Article/CJFDTOTAL-SHZN201901002.htm Li Xiuxian, Sun Min, Li Xiaodong, et al. Terrain Traversability Analysis Method for Air-Ground Collaborative Emergency[J]. Journal of Shihezi University(Natural Science), 2019, 37(1): 12-20 https://www.cnki.com.cn/Article/CJFDTOTAL-SHZN201901002.htm
[7]	Iagnemma K, Genot F, Dubowsky S. Rapid PhysicsBased Rough-Terrain Rover Planning with Sensor and Control Uncertainty[C]//IEEE International Conference on Robotics and Automation, Detroit, MI, USA, 1999
[8]	Lalonde J F, Vandapel N, Huber D F, et al. Natural Terrain Classification Using Three-Dimensional LiDAR Data for Ground Robot Mobility[J]. Journal of Field Robotics, 2006, 23(10): 839-861 doi: 10.1002/rob.20134
[9]	Larson J, Trivedi M. LiDAR Based Off-Road Negative Obstacle Detection and Analysis[C]//14th International IEEE Conference on Intelligent Transportation Systems(ITSC), Washington DC, USA, 2011
[10]	Kuthirummal S, Das A, Samarasekera S. A Graph Traversal Based Algorithm for Obstacle Detection Using LiDAR or Stereo[C]//IEEE/RSJ International Conference on Intelligent Robots and Systems, San Francisco, CA, USA, 2011
[11]	Langer D, Rosenblatt J K, Hebert M. A BehaviorBased System for Off-Road Navigation[J]. IEEE Transactions on Robotics and Automation, 1994, 10(6): 776-783 doi: 10.1109/70.338532
[12]	Gennery D B. Traversability Analysis and Path Planning for a Planetary Rover[J]. Autonomous Robots, 1999, 6(2): 131-146 doi: 10.1023/A:1008831426966
[13]	Kolter J Z, Rodgers M P, Ng A Y. A Control Architecture for Quadruped Locomotion over Rough Terrain[C]//IEEE International Conference on Robotics and Automation, Pasadena, CA, USA, 2008
[14]	Zucker M, Ratliff N, Stolle M, et al. Optimization and Learning for Rough Terrain Legged Locomotion [J]. The International Journal of Robotics Research, 2011, 30(2): 175-191 doi: 10.1177/0278364910392608
[15]	顾海燕, 李海涛, 闫利, 等. 地理本体驱动的遥感影像面向对象分析方法[J]. 武汉大学学报·信息科学版, 2018, 43(1): 31-36 doi: 10.13203/j.whugis20150468 Gu Haiyan, Li Haitao, Yan Li, et al. A Geographic Object-Based Image Analysis Methodology Based on Geo-ontology[J]. Geomatics and Information Science of Wuhan University, 2018, 43(1): 31-36 doi: 10.13203/j.whugis20150468
[16]	Ososinski M, Labrosse F. Automatic Driving on IllDefined Roads: An Adaptive, Shape-Constrained, Color-Based Method[J]. Journal of Field Robotics, 2015, 32(4): 504-533 doi: 10.1002/rob.21494
[17]	Mei J L, Yu Y F, Zhao H J, et al. Scene-Adaptive Off-Road Detection Using a Monocular Camera[J]. IEEE Transactions on Intelligent Transportation Systems, 2018, 19(1): 242-253 doi: 10.1109/TITS.2017.2768573
[18]	Holder C J, Breckon T P. Learning to Drive: Using Visual Odometry to Bootstrap Deep Learning for Off-Road Path Prediction[C]//IEEE Intelligent Vehicles Symposium(Ⅳ), Changshu, China, 2018
[19]	Faigl J, Prágr M. On Unsupervised Learning of Traversal Cost and Terrain Types Identification Using Self-Organizing Maps[M]//Artificial Neural Networks and Machine Learning–ICANN 2019: Theoretical Neural Computation. Cham: Springer, 2019: 654-668
[20]	Sutoh M, Otsuki M, Wakabayashi S, et al. The Right Path: Comprehensive Path Planning for Lunar Exploration Rovers[J]. IEEE Robotics & Automation Magazine, 2015, 22(1): 22-33 http://ieeexplore.ieee.org/document/7059362/citations
[21]	Zhang Y F, Wang W S, Bonatti R, et al. Integrating Kinematics and Environment Context into Deep Inverse Reinforcement Learning for Predicting OffRoad Vehicle Trajectories [EB/OL]. [2018-02- 16]. https://arxiv.org/pdf/1810.07225
[22]	Andrakhanov A, Stuchkov A. Traversability Estimation System for Mobile Robot in Heterogeneous Environment with Different Underlying Surface Characteristics[C]//12th International Scientific and Technical Conference on Computer Sciences and Information Technologies(CSIT), Lviv, Ukraine, 2017
[23]	刘浩敏, 章国锋, 鲍虎军. 基于单目视觉的同时定位与地图构建方法综述[J]. 计算机辅助设计与图形学学报, 2016, 28(6): 855-868 doi: 10.3969/j.issn.1003-9775.2016.06.001 Liu Haomin, Zhang Guofeng, Bao Hujun. A Survey of Monocular Simultaneous Localization and Mapping[J]. Journal of Computer-Aided Design & Computer Graphics, 2016, 28(6): 855-868 doi: 10.3969/j.issn.1003-9775.2016.06.001
[24]	李小倩, 何伟, 朱世强, 等. 基于环境语义信息的同步定位与地图构建方法综述[J]. 工程科学学报, 2021, 43(6): 754-767 https://www.cnki.com.cn/Article/CJFDTOTAL-BJKD202106004.htm Li Xiaoqian, He Wei, Zhu Shiqiang, et al. Survey of Simultaneous Localization and Mapping Based on Environmental Semantic Information[J]. Chinese Journal of Engineering, 2021, 43(6): 754-767 https://www.cnki.com.cn/Article/CJFDTOTAL-BJKD202106004.htm
[25]	Chen Z X, Xu X C, Wang Y, et al. Deep Phase Correlation for End-to-End Heterogeneous Sensor Measurements Matching [EB/OL]. [2020-03-01]. https://arxiv. org/abs/2008. 09474
[26]	刘阳, 于兴超, 贾占永. 面向车辆通过性的地理因子分析与应用[J]. 国防科技, 2020, 41(5): 105-110 https://www.cnki.com.cn/Article/CJFDTOTAL-GFCK202005018.htm Liu Yang, Yu Xingchao, Jia Zhanyong. Geographical Factor Analysis and Application for Vehicle Trafficability[J]. National Defense Technology, 2020, 41(5): 105-110 https://www.cnki.com.cn/Article/CJFDTOTAL-GFCK202005018.htm
[27]	Singh S, Simmons R, Smith T, et al. Recent Pro gress in Local and Global Traversability for Planetary Rovers[C]//IEEE International Conference on Robotics and Automation, San Francisco, CA, USA, 2000
[28]	Ronneberger O, Fischer P, Brox T. U-Net: Convolutional Networks for Biomedical Image Segmentation [C]//Medical Image Computing and Computer-Assisted Intervention, Munich, Germany, 2015
[29]	Oktay O, Schlemper J, Folgoc L L, et al. Attention U Net: Learning Where to Look for the Pancreas [EB/OL]. [2020-03-01]. https://arxiv.org/pdf/1804.03999
[30]	Duchi J, Hazan E, Singer Y. Adaptive Subgradient Methods for Online Learning and Stochastic Optimization[J]. The Journal of Machine Learning Research, 2011, 12(1-2): 2 121-2 159 http://web.stanford.edu/~jduchi/projects/DuchiHaSi10.html

[1]	WANG Yong, HAN Yaoyao, LIU Jiping, CAO Yuanhui, CHEN Hongyu, KANG Mengjun, ZHU Jun. Emergency Rescue Geospatial Intelligence: Conceptual Characteristics, Generation Technologies, and Application Practices[J]. Geomatics and Information Science of Wuhan University.
[2]	ZHU Litao, SHEN Jie, WANG Xing, ZHOU Jingyi, HOU Yingxu, ZHANG Cheng. An Extraction Method of Emotional Landmarks in Large Malls Based on User-Generated Content[J]. Geomatics and Information Science of Wuhan University, 2024, 49(9): 1693-1701. DOI: 10.13203/j.whugis20210488
[3]	LI Xiaolin, LI Gang, ZHANG Enqi, GU Guanghua. Determinant Point Process Sampling Method for Text‑to‑Image Generation[J]. Geomatics and Information Science of Wuhan University, 2024, 49(2): 246-255. DOI: 10.13203/j.whugis20210373
[4]	HOU Xujuan, DENG Xiaotong, HUA Weihua, YIN Wanting, LI Peng, QI Chunyu. DEM Super-resolution Reconstruction Method Based on Adaptive Generative Adversarial Network[J]. Geomatics and Information Science of Wuhan University. DOI: 10.13203/j.whugis20240186
[5]	LU Chuanwei, SUN Qun, ZHAO Yunpeng, SUN Shijie, MA Jingzhen, CHENG Mianmian, LI Yuanfu. A Road Extraction Method Based on Conditional Generative Adversarial Nets[J]. Geomatics and Information Science of Wuhan University, 2021, 46(6): 807-815. DOI: 10.13203/j.whugis20190159
[6]	TAN Guoxin, SUN Chuanming. An Interactive Approach to Generate Realistic 3DFace[J]. Geomatics and Information Science of Wuhan University, 2014, 39(8): 992-997. DOI: 10.13203/j.whugis20130152
[7]	XU Yanyan, XU Zhengquan, ZHANG Yuxia. A High Efficient Content Security Protection Method Suitable for Remote Sensing Image[J]. Geomatics and Information Science of Wuhan University, 2012, 37(8): 936-939.
[8]	WANG Jiechen, SHEN Dingtao, CUI Can. RLE-B Algorithm for Buffer Generation[J]. Geomatics and Information Science of Wuhan University, 2010, 35(9): 1121-1124.
[9]	Huang Jiana, Wu Junchang. Reliability Analysis and Gross Error Detection of Traverse Network[J]. Geomatics and Information Science of Wuhan University, 1997, 22(1): 51-54.
[10]	He Zongyi. A Study of the Method for Measuring the Information Content of Map[J]. Geomatics and Information Science of Wuhan University, 1987, 12(1): 70-80.

Cited By

Get Citation

PDF

XML

Article views (1185) PDF downloads (93)

A Data-driven Method for Traversability Analysis and Dataset Generation on Extraterrestrial Terrain

Abstract

References

Related Articles

Catalog

Related

A Data-driven Method for Traversability Analysis and Dataset Generation on Extraterrestrial Terrain

Abstract

References

Related Articles

Catalog

Related

Export File

Citation

Format

Content