Research Progress of Non-geometric Hazard Perception for Unmanned Planetary Rover
-
摘要: 提升星球车的环境感知能力是提高系统智能性、自主性的前提,非几何障碍感知是其中关键的一环。通过回顾星球车非几何障碍感知发展历程,梳理出非几何障碍感知内容分为当前障碍估测和前方障碍预测两大类;对障碍估测和障碍预测涉及到的沉陷量估测、滑移率估测、星壤参数在线识别、地形分类等国内外研究现状进行了介绍和评述分析,总结得出:未来非几何障碍识别研究应多关注轮地力学模型优化、多源信息融合感知和人工智能技术应用;对基于星壤参数识别的滑移预测方法进行了阐述。Abstract: Improving the environment perception ability is a prerequisite for improving the intelligence and autonomy of the rover. Non-geometric hazard perception is the key part of autonomous navigation. Reviewing the development of the non-geometric hazard perception of the rover, it shows that the key aspects of the non-geometric hazard perception are hazard estimation and hazard prediction. Non-geometric hazard estimation and prediction include wheel-soil model, wheel sinkage estimation, slip ratio estimation, identification of soil parameters and terrain classification, and the relevant research on theses aspects are introduced and analyzed. The future research on non-geometric hazard perception should focus on the optimization of wheel-soil interaction mechanics model, multi-source information fusion and the application of artificial intelligence technology. Finally, a slip ratio prediction method based on soil parameter identification is described.
-
Key words:
- planetary rover /
- environment perception /
- non-geometric hazard /
- slip prediction
Highlights● Non-geometric hazard perception is divided into two categories:hazard estimation and hazard prediction. ● Future research on non-geometric obstacles should focus on the following aspects,including the optimization of wheel-soil interaction mechanics model,multi-source information fusion and the application of artificial intelligence technology. ● A slip ratio prediction method based on soil parameter identification is described. -
表 1 无人星球车非几何障碍感知技术
Table 1 Non-geometric hazard perception of unmanned planetary rover
星球车 非几何障碍感知 “月球1号”(Luna-1)/ “月球2号”(Luna-2)
(1970/1973年,前苏联,月球)由获取非驱动轮与驱动轮转数估测打滑 “索杰纳号”(Sojourner)(1996年,美国,火星) 通过电机电流大小估测牵引系数来表征地面力学特性 “勇气号”(Spirit)/“机遇号”(Opportunity)(2004年,美国,火星) 视觉测程法估测滑移率 “好奇号”(Curiosity)(2012年,美国,火星) 视觉测程法估测滑移率,车辙辅助估测滑移,通过SPOC-G软件预测前方滑移率 “玉兔号”(Yutu)/“玉兔2号”(Yutu-2)(2013/2019年,中国,月球) 视觉测程法估测滑移率,车辙信息辅助判断沉陷量 表 2 星壤参数
Table 2 Parameter of soil
参数 代表意义 参数 代表意义 ${k_c}$ 星壤内聚力模量 ${k_\varphi }$ 星壤内摩擦力模量 $c$ 星壤内聚力 $\varphi $ 星壤内摩擦角 K 星壤剪切弹性模量 n 沉陷指数 ${c_{\rm{2}}}$ 与最大应力角位置相关的车轮接触角系数 ${c_{\rm{1}}}$ 与车轮进入角位置相关的车轮接触角系数 表 3 基于经典轮地力学模型的星壤参数在线识别研究
Table 3 Research on soil parameter online identification based on classic wheel-soil interaction mechanics model
提出人 求解过程 求解参数 提出人 求解过程 求解参数 Iagnemma[28-29] 简化垂直载荷W和转动扭矩T模型,使用线性最小二乘法在线识别 c $\varphi $ 崔平远[32] 运用两点高斯求积公式对力学模型进行简化,先由最速下降法求取一组近似值,再将近似值作为初值运用于牛顿迭代法进行参数求解 n ${k_c}$ ${k_\varphi }$ Hutangkabodee[30] 复合辛普森积分对挂钩牵引力进行近似求解,采用牛顿迭代法进行识别 $\varphi $ ${k_c}/b + {k_\varphi }$ K Meng[33] 简化力学模型,采用线性最小二乘法与牛顿迭代法 $\varphi $ ${k_c}/b + {k_\varphi }$ K Cross[31] 通过多层感知机算法对c和$\varphi $进行在线估计 c $\varphi $ 丁亮[34] 采用龙贝格积分法和应力分布线性化方法简化模型,分步采用改进牛顿算法和拟牛顿算法分别对剪切特性参数和承压特性参数进行识别 c $\varphi $ ${k_c}/b + {k_\varphi }$ K 表 4 用于地形分类的6类分类器效果对比
Table 4 Comparison of the effects of six classifiers for terrain classifications
分类器 训练及分类时间 分类效果 SVM 训练最慢,分类快 精度最高 kNN 训练最快、分类较慢 精度较高 Brooks 训练较慢,分类最快 精度较差 PNN 训练较快,分类最慢 精度相对较差 贝叶斯 训练较快、分类一般 精度相对较差 决策树 训练较慢、分类较慢 精度相对较差 -
[1] 叶培建,黄江川,孙泽洲,等. 中国月球探测器发展历程和经验初探[J]. 中国科学:技术科学,2014,44(6):543-558. doi: 10.1360/N092014-00150YE P J,HUANG J C,SUN Z Z,et al. A the development history and experience of Chinese lunar explorer[J]. Scientia Sinica Technologica,2014,44(6):543-558. doi: 10.1360/N092014-00150 [2] 邢琰,滕宝毅,刘祥,等. 月球表面巡视探测GNC技术[J]. 空间科学学报,2016,36(2):196-201. doi: 10.11728/cjss2016.02.196XING Y,TENG B Y,LIU X,et al. Guidance,navigation and control technology for lunar surface exploration[J]. Chinese Journal of Space Science,2016,36(2):196-201. doi: 10.11728/cjss2016.02.196 [3] 刘冰. 月面地形识别与力学参数估计技术研究[D]. 北京: 北京工业大学, 2008.LIU B. Research on terrain identification and mechanical parameters estimation of lunar soil[D]. Beijing: Beijing University of Technology, 2008. [4] 李静文. 月面巡视区域地形与巡视器通过性统计分析[J]. 中国科学:技术科学,2015,45(7):773-778.LI J W. Statistic analysis of exploration area topography and rover trafficability[J]. Scientia Sinica:Technologica,2015,45(7):773-778. [5] WILCOX B H. Non-geometric hazard detection for a Mars microrover[C]//Conference on Intelligent Robotics in Field, Factory, Service, and Space. Washington, DC: [s. n.], 1994. [6] GONZALEZ R,APOSTOLOPOILOS D,IAGNEMMA K. Slippage and immobilization detection for planetary exploration rovers via machine learning and proprioceptive sensing[J]. Journal of Field Robotics,2018,35(2):231-47. doi: 10.1002/rob.21736 [7] 陈百超,邹猛,党兆龙,等. CE-3月球车筛网轮月面沉陷行为试验[J]. 吉林大学学报(工学版),2019,49(6):1836-1843.CHEN B C,ZOU M,DANG Z L,et al. Experiment on pressure-sinkage for mesh wheels of CE-3 lunar rover on lunar regolith[J]. Journal of Jilin University (Engineering and Technology Edition),2019,49(6):1836-1843. [8] IEGNEMMA K, BROOKS C, DUBOWSKY S. Visual, tactile, and vibration-based terrain analysis for planetary rovers[C]//IEEE Aerospace Conference. [S. l.]: IEEE, 2004. [9] REINA G,OJEDA L,MILELLA A,et al. Wheel slippage and sinkage detection for planetary rovers[J]. IEEE/ASME Transactions on Mechatronics,2006,11(2):185-195. doi: 10.1109/TMECH.2006.871095 [10] REINA G, MILELLA A, PANELLA F W. Vision-based wheel sinkage estimation for rough-terrain mobile robots[C]//15th International Conference on Mechatronics and Machine Vision in Practice. Auckland: [s. n.], 2008. [11] HEGDE G P, ROBINSON C J, YE C, et al. Computer vision based wheel sinkage detection for robotic lunar exploration tasks[C]//IEEE International Conference on Mechatronics and Automation. Xi’an: IEEE, 2010. [12] HEGDE G M,CANG Y,ROBINSON C A,et al. Computer-vision-based wheel sinkage estimation for robot navigation on lunar terrain[J]. IEEE/ASME Transactions on Mechatronics,2013(4):1346-1356. [13] GAO H B,LV F T,YUAN B F,et al. Sinkage definition and visual detection for planetary rovers wheels on rough terrain based on wheel-soil interaction boundary[J]. Robotics and Autonomous Systems,2017,98:222-240. doi: 10.1016/j.robot.2017.09.011 [14] NISTER D, NARODITSKY O, BERGEN J. Visual odometry[C]//IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Princeton, USA: IEEE, 2004. [15] MAIMONE M,CHENG Y,MATTHIES L. Two years of visual odometry on the Mars exploration rovers[J]. Journal of Field Robotics,2007,24(3):169-186. doi: 10.1002/rob.20184 [16] GONZALEZ R,RODRIGUEZ F,GUZMN J L,et al. Combined visual odometry and visual compass for off-road mobile robots localization[J]. Robotica,2012,30(6):865-878. doi: 10.1017/S026357471100110X [17] DING L,GAO H B,FENG Z Q,et al. Experimental study and analysis on driving wheels’ performance for planetary exploration rovers moving in deformance soil[J]. Journal of Terramechanics,2011,48:27-45. doi: 10.1016/j.jterra.2010.08.001 [18] LI N, DING L, GAO H B, et al. Detection method for planet rover slip ratio based on vision measuring technology[C]//The 35th Chinese Control Conference. Xi’an, China: [s. n.], 2013. [19] 李楠,高海波,吕凤天,等. 车辙图像频域分析及星球车车轮滑转率估计方法[J]. 宇航学报,2016,37(11):1356-1364. doi: 10.3873/j.issn.1000-1328.2016.11.010LI N,GAO H B,LV F T,et al. Wheel trace imprint image frequency domain analysis and rover wheel slip ratio estimation[J]. Journal of Astronautics,2016,37(11):1356-1364. doi: 10.3873/j.issn.1000-1328.2016.11.010 [20] 吕凤天,高海波,李楠,等. 基于单目视觉的松软地面星球车车轮滑转率估计[J]. 机械工程学报,2019,56(2):77-85.LYU F T,GAO H B,Li N,et al. Monocular vision-based estimation of wheel slip ratio for planetary rovers in soft terrain[J]. Journal of Mechanical Engineering,2019,56(2):77-85. [21] 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 [22] GONZALEZ R,LAGNEMMA K. Slippage estimation and compensation for planetary exploration rovers. State of the art and future challenges[J]. Journal of Field Robotics,2019,35(4):564-577. [23] ROTHROCK B, KENNEDY R, CUNNINGHAM C, et al. Spoc: deep learning-based terrain classification for Mars rover missions[C]//Space Conference and Exposition. Long Beach, California: [s. n.]: 2016. [24] 孙晶. 软地面轮−土作用力学参数在线识别[D]. 上海: 上海大学, 2015.SUN J. On-line deformable terrain parameter identification based on wheel-terrain interaction mechanics[D]. Shanghai: Shanghai University, 2015. [25] MOORE H J,HUTTON R E,SCOTT R F,et al. Surface materials of the viking landing sites[J]. Journal of Geophysical Research,1977,82(28):4497-4523. doi: 10.1029/JS082i028p04497 [26] CRISP J,MATIJEVIC J R. Characterization of the martian surface deposits by the Mars Pathfinder Rover,Sojourner[J]. Science,1997,278(5344):1765-1768. doi: 10.1126/science.278.5344.1765 [27] LI M, GAO F, SUN P, et al. The algorithm research of terrain parameter estimation based on lunar rover's traveling information[C]//International Conference on Optoelectronics and Image Processing. Haikou: [s. n.], 2010. [28] LIU Z,GUO J,DING L,et al. Online estimation of terrain parameters and resistance force based on equivalent sinkage for planetary rovers in longitudinal skid[J]. Mechanical Systems and Signal Processing,2019,119(15):39-54. [29] IAGNEMMA K,KANG S,SHIBLY H,et al. Online terrain parameter estimation for wheeled mobile robots with application to planetary rovers[J]. IEEE Transactions on Robotics,2004,20(5):921-927. doi: 10.1109/TRO.2004.829462 [30] IGNEMMA K, SHIBLY H, DUBOWSKY S. On-line terrain parameter estimation for planetary rovers[C]//IEEE International Conference on Robotics and Automation. [S. l.]: IEEE, 2002. [31] 崔平远,刘冰,居鹤华. 月壤力学参数在线估计算法研究[J]. 计算机测量与控制,2008,16(2):245-269.CUI P Y,LIU B,JU H H. Research on mechanical parameters online estimation of lunar soil[J]. Computer Measurement & Control,2008,16(2):245-269. [32] HUTANGKABODEE S, ZWEIRI Y H, SENEVIRATNE L D, et al. Performance prediction of a wheeled vehicle on unknown terrain using identified soil parameters[C]//IEEE International Conference on Robotics and Automation. [S. l.]: IEEE, 2006. [33] CROSS M,ELLERY A,QADI A. Estimating terrain parameters for a rigid wheeled rover using neural networks[J]. Journal of Terramechanics,2013,50(3):165-174. doi: 10.1016/j.jterra.2013.04.002 [34] 丁亮. 月/星球车轮地作用地面力学模型及其应用研究[D]. 哈尔滨: 哈尔滨工业大学, 2009.Ding L. Wheel-soil interaction terramechanics for lunar/planetary exploration rovers: modeling and application[D]. Harbin: Harbin Institute of Technology, 2009. [35] HOWARD A,SERAJI H. Vision-based terraincharacterization and traversability assessment[J]. Journal of Robotics System,2001,18(10):577-587. doi: 10.1002/rob.1046 [36] CHHANIYARA S,BRUNSKILL C,YEOMANS B,et al. Terrain trafficability analysis and soil mechanical property identification for planetary rovers:a survey[J]. Journal of Terramechanics,2012,49(2):115-128. doi: 10.1016/j.jterra.2012.01.001 [37] HEVERLY M,MATTHEWS J,LIN J,et al. Traverse performance characterization for the Mars Science Laboratory Rover[J]. Journal of Field Robotics,2013,30(6):835-846. doi: 10.1002/rob.21481 [38] CUNNINGHAM C, ONO M, NESNAS I, et al. Locally-adaptive slip prediction for planetary rovers using Gaussian processes[C]//2017 IEEE International Conference on Robotics and Automation (ICRA). [S. l.]: IEEE, 2017. [39] SADHUKHAN D AND MOORE C. Online terrain estimation using internal sensors[C]//Proceedings of the Florida Conference on Recent Advances in Robotics. Boca Raton, USA: [s. n.], 2013. [40] WEISS C, FECHNER N, STARK M, et al. Comparison of different approaches to vibration-based terrain classification[C]//European Conference on Mobile Robotics. Freiburg, Germany: [s. n.], 2007. [41] BROOKS C A,IAGNEMMA K. Self-supervised terrain classification for planetary surface exploration rovers[J]. Journal of Field Robotics,2012,29(3):445-468. doi: 10.1002/rob.21408 [42] 叶培建, 孟林智, 马继楠, 等. 深空探测人工智能技术应用及发展建议[J]. 深空探测学报(中英文), 2019, 6(4): 303-316.YE P J, MENG L Z, MA J N, et al. Suggestions on artificial intelligence technology application and development in deep space exploration[J]. 2019, 6(4): 303-316. [43] 郭延宁,冯振,马广富,等. 行星车视觉导航与自主控制进展与展望[J]. 宇航学报,2018,39(11):1185-1196.GUO Y N,FENG Z,MA G F,et al. Advances and trends in visual navigation and autonomous control of a planetary rover[J]. Journal of Astronautics,2018,39(11):1185-1196. [44] 刘付成. 人工智能在航天器控制中的应用[J]. 飞控与探测,2018,1(1):16-25.LIU F C. Application of artificial intelligence in spacecraft[J]. Flight Control & Detection,2018,1(1):16-25. -
计量
- 文章访问数: 22
- 被引次数: 0