浏览全部资源
扫码关注微信
1.江西农业大学 工学院,江西 南昌 330045
2.中国空间技术研究院 北京空间飞行器总体设计部,北京 100094
3.吉林大学 工程仿生教育部重点实验室,吉林 长春 130022
[ "薛 龙(1977-),男,辽宁本溪人,博士,副教授,硕士生导师,2017年于吉林大学获得博士学位,主要从事地面力学、仿生科学、智能农机等方面的研究。E-mail: ultimata@163.com" ]
[ "黎 静(1978-),女,江西宜春人,博士,副教授,硕士生导师,2014年于中国农业大学获得博士学位,主要从事智能农机、机器视觉等方面的研究。E-mail:lijing3815@163.com" ]
收稿日期:2022-06-06,
修回日期:2022-07-26,
纸质出版日期:2023-03-10
移动端阅览
薛龙,李澜,党兆龙等.复杂地面车辙识别试验与验证[J].光学精密工程,2023,31(05):581-587.
XUE Long,LI Lan,DANG Zhaolong,et al.Test and verification of rut recognition on complex ground[J].Optics and Precision Engineering,2023,31(05):581-587.
薛龙,李澜,党兆龙等.复杂地面车辙识别试验与验证[J].光学精密工程,2023,31(05):581-587. DOI: 10.37188/OPE.20233105.0581.
XUE Long,LI Lan,DANG Zhaolong,et al.Test and verification of rut recognition on complex ground[J].Optics and Precision Engineering,2023,31(05):581-587. DOI: 10.37188/OPE.20233105.0581.
火星表面地形地貌复杂,为了保证火星车行驶安全,需要对巡视器周边土壤的图像信息进行判别和分类。首先,根据试验场地和图像信息等对图像进行预处理,建立鸟瞰图像。接着,以鸟瞰图像为基础建立图像块并建立数据集,建模集和预测集分别包含315组和135组数据。然后,在划分的数据集基础上建立神经网络模型,并对数据进行训练和分类。最后,根据得到的分类模型对图像进行分类,得到感兴趣区域。分类结果表明:应用ResNet50得到的模型其建模集和预测集的分类准确率分别为75.56%和81.48%。该方法可实现巡视器周边地表类型的分类,并提取图像的感兴趣区域,以便实现更为精准的判别,可用于实现火星车通过性感知、风险预测和路径规划,为未来智能星球车移动系统研制和探测提供理论和技术支持。
The geomorphological characterization of Mars is complex. Therefore, to ensure the safe driving of rover, it is essential to understand the surface state around the rover through images captured by on-board digital cameras. The images are first preprocessed using stereo vision to create an aerial view, which is then divided into equal-sized blocks. Next, calibration and prediction datasets are created, containing 315 and 135 datapoints, respectively. Based on these datasets, a neural network model is developed. Finally, the image is classified using the resulting classification model to identify the region of interest. The results of the classification show that its accuracy on the calibration and prediction datasets using ResNet50 is 75.56% and 81.48%, respectively. This method can help researchers characterize the surface types around UGVs and identify the regions of interest that may provide more valuable information from the images. It can also be used for traversability prediction, risk assessment, and automatic path planning.
薛龙 , 党兆龙 , 陈百超 , 等 . 地面力学在火星壤力学参数估计研究中的进展与展望 [J]. 宇航学报 , 2020 , 41 ( 2 ): 136 - 146 .
XUE L , DANG Z L , CHEN B C , et al . Advances and prospects of Martian soil parameter identification based on terramechanics [J]. Journal of Astronautics , 2020 , 41 ( 2 ): 136 - 146 . (in Chinese)
ARVIDSON R E , BELL J F I , BELLUTTA P , et al . Spirit Mars Rover Mission: overview and selected results from the northern Home Plate Winter Haven to the side of Scamander crater [J]. Journal of Geophysical Research: Planets , 2010 , 115 ( E7 ): E00 F 03 . doi: 10.1029/2010je003633 http://dx.doi.org/10.1029/2010je003633
郑燕红 , 邓湘金 , 顾征 , 等 . 嫦娥五号月面表取采样点选择 [J]. 光学 精密工程 , 2021 , 29 ( 12 ): 2935 - 2943 . doi: 10.37188/OPE.20212912.2935 http://dx.doi.org/10.37188/OPE.20212912.2935
ZHENG Y H , DENG X J , GU Z , et al . Lunar surface sampling point selection of Chang'E 5 [J]. Opt. Precision Eng. , 2021 , 29 ( 12 ): 2935 - 2943 . (in Chinese) . doi: 10.37188/OPE.20212912.2935 http://dx.doi.org/10.37188/OPE.20212912.2935
黄敬涛 , 王晓东 , 孙振亚 , 等 . 天问一号高分相机火表复杂照度下自动调光成像电路设计 [J]. 光学 精密工程 , 2022 , 30 ( 2 ): 191 - 198 . doi: 10.37188/OPE.20223002.0191 http://dx.doi.org/10.37188/OPE.20223002.0191
HUANG J T , WANG X D , SUN Z Y , et al . Design of auto-exposure imaging circuit under complex illuminance of Mars in Tianwen-1 high-resolution camera [J]. Opt. Precision Eng. , 2022 , 30 ( 2 ): 191 - 198 . (in Chinese) . doi: 10.37188/OPE.20223002.0191 http://dx.doi.org/10.37188/OPE.20223002.0191
GONZALEZ R , CHANDLER S , APOSTOLOPOULOS D . Characterization of machine learning algorithms for slippage estimation in planetary exploration rovers [J]. Journal of Terramechanics , 2019 , 82 : 23 - 34 . doi: 10.1016/j.jterra.2018.12.001 http://dx.doi.org/10.1016/j.jterra.2018.12.001
MA H , YANG H , LI Q Z , et al . A geometry-based slip prediction model for planetary rovers [J]. Computers & Electrical Engineering , 2020 , 86 : 106749 . doi: 10.1016/j.compeleceng.2020.106749 http://dx.doi.org/10.1016/j.compeleceng.2020.106749
刘维 , 徐珺楠 , 金玳冉 , 等 . 基于CNN-SPGD算法的相干光通信像差校正方法研究 [J]. 光学 精密工程 , 2022 , 30 ( 6 ): 743 - 754 . doi: 10.37188/OPE.20223006.0743 http://dx.doi.org/10.37188/OPE.20223006.0743
LIU W , XU J N , JIN D R , et al . Research on aberration correction method of coherent optical communication based on CNN-SPGD algorithm [J]. Opt. Precision Eng. , 2022 , 30 ( 6 ): 743 - 754 . (in Chinese) . doi: 10.37188/OPE.20223006.0743 http://dx.doi.org/10.37188/OPE.20223006.0743
刘可佳 , 马荣生 , 唐子木 , 等 . 采用优化卷积神经网络的红外目标识别系统 [J]. 光学 精密工程 , 2021 , 29 ( 4 ): 822 - 831 . doi: 10.37188/OPE.20212904.0822 http://dx.doi.org/10.37188/OPE.20212904.0822
LIU K J , MA R S , TANG Z M , et al . Design of infrared target recognition system with optimized convolutional neural network [J]. Opt. Precision Eng. , 2021 , 29 ( 4 ): 822 - 831 . (in Chinese) . doi: 10.37188/OPE.20212904.0822 http://dx.doi.org/10.37188/OPE.20212904.0822
袁宝峰 , 王成恩 , 邹猛 , 等 . 火星车主动悬架设计及蠕动脱困策略 [J]. 吉林大学学报(工学版) , 2021 , 51 ( 1 ): 154 - 162 . doi: 10.13229/j.cnki.Jdxbgxb20200604 http://dx.doi.org/10.13229/j.cnki.Jdxbgxb20200604
YUAN B F , WANG C G , ZOU M , et al . Design active suspension system and creeping control strategy for Mars rover of China [J]. Journal of Jilin University (Engineering and Technology Edition) , 2021 , 51 ( 1 ): 154 - 162 . (in Chinese) . doi: 10.13229/j.cnki.Jdxbgxb20200604 http://dx.doi.org/10.13229/j.cnki.Jdxbgxb20200604
GONZÁLEZ R , LÓPEZ A , IAGNEMMA K . Thermal vision, moisture content, and vegetation in the context of off-road mobile robots [J]. Journal of Terramechanics , 2017 , 70 : 35 - 48 . doi: 10.1016/j.jterra.2017.01.001 http://dx.doi.org/10.1016/j.jterra.2017.01.001
PIQUEUX S , CHRISTENSEN P R . A model of thermal conductivity for planetary soils: 1. Theory for unconsolidated soils [J]. Journal of Geophysical Research: Planets , 2009 , 114 ( E9 ): E09005 . doi: 10.1029/2008je003308 http://dx.doi.org/10.1029/2008je003308
XUE L , LI J Q , ZOU M , et al . In situ identification of shearing parameters for loose lunar soil using least squares support vector machine [J]. Aerospace Science and Technology , 2016 , 53 : 154 - 161 . doi: 10.1016/j.ast.2016.03.018 http://dx.doi.org/10.1016/j.ast.2016.03.018
DING L , GAO H B , LIU Z , et al . Identifying mechanical property parameters of planetary soil using in situ data obtained from exploration rovers [J]. Planetary and Space Science , 2015 , 119 : 121 - 136 . doi: 10.1016/j.pss.2015.09.003 http://dx.doi.org/10.1016/j.pss.2015.09.003
RINGDAHL O , HELLSTRÖM T , WÄSTERLUND I , et al . Estimating wheel slip for a forest machine using RTK-DGPS [J]. Journal of Terramechanics , 2012 , 49 ( 5 ): 271 - 279 . doi: 10.1016/j.jterra.2012.08.003 http://dx.doi.org/10.1016/j.jterra.2012.08.003
LI W H , LIU Z , GAO H B , et al . Soil parameter modification used for boosting predictive fidelity of planetary rover's slippage [J]. Journal of Terramechanics , 2014 , 56 : 173 - 184 . doi: 10.1016/j.jterra.2014.10.001 http://dx.doi.org/10.1016/j.jterra.2014.10.001
0
浏览量
611
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构