In situ identification of shearing parameters for loose lunar soil using least squares support vector machine

Abstract A method is presented for the online prediction of the terrain-shearing parameters for a wheeled Unmanned Ground Vehicles (UGVs) traversing on an unknown terrain. The method uses a trained multiple-output least squares support vector machine (LS_SVM) to map engineering data and predict the terrain-shearing parameters such as cohesion, internal friction angle and shear deformation modulus without requiring information on wheel sinkage. The predicted terrain-shearing parameters can be used to predict vehicle drawbar pull which can be used for trafficability prediction, traction control and performance optimization. Experiments were performed using a single-wheel soil bin to measure the sinkage, drawbar pull and torque for a griddle net wheel under different slip ratio. An additional experiment was performed under a continuous slip ratio from 0.2 to 0.6 with a wheel load of 50 N to validate the method. The experimental results show that the multiple output LS_SVM model can accurately predict the terrain-shearing parameters using the slip ratio, torque and wheel load without the need of wheel sinkage.

[1]  Karl Iagnemma,et al.  Vibration-based terrain classification for planetary exploration rovers , 2005, IEEE Transactions on Robotics.

[2]  Steven Dubowsky,et al.  An equivalent soil mechanics formulation for rigid wheels in deformable terrain, with application to planetary exploration rovers , 2005 .

[3]  Kaspar Althoefer,et al.  Performance prediction of a wheeled vehicle on unknown terrain using identified soil parameters , 2006, Proceedings 2006 IEEE International Conference on Robotics and Automation, 2006. ICRA 2006..

[4]  Kazuya Yoshida,et al.  Parameter identification for planetary soil based on a decoupled analytical wheel-soil interaction terramechanics model , 2009, 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[5]  Jo Yung Wong,et al.  Theory of ground vehicles , 1978 .

[6]  Zongquan Deng,et al.  ROSTDyn: Rover simulation based on terramechanics and dynamics , 2013 .

[7]  R. Yousefi Moghaddam,et al.  Method and apparatus for on-line estimation of soil parameters during excavation , 2012 .

[8]  Adel Dameshghi,et al.  Improving RTDGPS accuracy using hybrid PSOSVM prediction model , 2014 .

[9]  Zongquan Deng,et al.  A method for on-line soil parameters modification to planetary rover simulation , 2012 .

[10]  M. G. Bekker.  Introduction to Terrain-Vehicle Systems , 1969 .

[11]  A. Okello,et al.  A review of soil strength measurement techniques for prediction of terrain vehicle performance , 1991 .

[12]  Keiji Nagatani,et al.  Experimental study and analysis on driving wheels' performance for planetary exploration rovers moving in deformable soil , 2011 .

[13]  Steven Dubowsky,et al.  On-line terrain parameter estimation for planetary rovers , 2002, Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No.02CH37292).

[14]  Y.H. Zweiri,et al.  Identification of soil parameters for unmanned ground vehicles track-terrain interaction dynamics , 2004, SICE 2004 Annual Conference.

[15]  Raymond E. Arvidson,et al.  Physical properties and localization investigations associated with the 2003 Mars Exploration rovers , 2003 .

[16]  Kaspar Althoefer,et al.  The modelling and estimation of driving forces for unmanned ground vehicles in outdoor terrain , 2009, Int. J. Model. Identif. Control..

[17]  K Davis,et al.  Localization and Physical Property Experiments Conducted by Opportunity at Meridiani Planum , 2004, Science.

[18]  Alex Ellery,et al.  Estimating terrain parameters for a rigid wheeled rover using neural networks , 2013 .

[19]  Johan A. K. Suykens,et al.  Multiclass least squares support vector machines , 1999, IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339).

[20]  William H. Farrand,et al.  Overview of the Opportunity Mars Exploration Rover mission to Meridiani Planum: Eagle crater to Purgatory ripple , 2006 .

[21]  Hutao Cui,et al.  Vision-aided inertial navigation for pinpoint planetary landing , 2007 .

[22]  Kuang-Yao Lee,et al.  Multiclass support vector classification via coding and regression , 2010, Neurocomputing.

[23]  Steven Dubowsky,et al.  Online terrain parameter estimation for wheeled mobile robots with application to planetary rovers , 2004, IEEE Transactions on Robotics.

[24]  Johan A. K. Suykens,et al.  Least Squares Support Vector Machines , 2002 .

[25]  Y.H. Zweiri,et al.  Online soil parameter estimation scheme based on Newton-Raphson method for autonomous excavation , 2005, IEEE/ASME Transactions on Mechatronics.

[26]  Rover Team.  Characterization of the Martian surface deposits by the Mars Pathfinder rover, Sojourner. Rover Team. , 1997, Science.

[27]  Kaspar Althoefer,et al.  Soil parameter identification for wheel-terrain interaction dynamics and traversability prediction , 2006, Int. J. Autom. Comput..

[28]  Johan A. K. Suykens,et al.  Multiclass LS-SVMs: Moderated Outputs and Coding-Decoding Schemes , 2002, Neural Processing Letters.

[29]  Jeffrey R. Johnson,et al.  Spirit Mars Rover Mission: Overview and selected results from the northern Home Plate Winter Haven to the side of Scamander crater , 2010 .

[30]  D. Ming,et al.  Localization and Physical Properties Experiments Conducted by Spirit at Gusev Crater , 2004, Science.

[31]  A. R. Reece,et al.  Prediction of rigid wheel performance based on the analysis of soil-wheel stresses , 1967 .

[32]  Gary D. Clow,et al.  A summary of Viking sample-trench analyses for angles of internal friction and cohesions , 1982 .

[33]  Zongquan Deng,et al.  Wheel slip-sinkage and its prediction model of lunar rover , 2010 .

[34]  Lu Yan.  An approach of Identifying Mechanical Parameters for Lunar Soil Based on Integrated Wheel-Soil Interaction Terramechanics Model of Rovers , 2011 .

[35]  A. R. Reece,et al.  Prediction of rigid wheel performance based on the analysis of soil-wheel stresses part I. Performance of driven rigid wheels , 1967 .

[36]  Johan A. K. Suykens,et al.  Kernel based partially linear models and nonlinear identification , 2005, IEEE Transactions on Automatic Control.

[37]  R. Anderson,et al.  Cohesions, friction angles, and other physical properties of Martian regolith from Mars Exploration Rover wheel trenches and wheel scuffs , 2011 .

[38]  Jiancheng Fang,et al.  An innovative high-precision SINS/CNS deep integrated navigation scheme for the Mars rover , 2014 .