Diagonal recurrent neural networks for parameters identification of terrain based on wheel–soil interaction analysis

Wheeled mobile robots (WMR) are often applied to travel on outdoor unstructured environment, such as loose soil or variable field terrain. Learning the knowledge of terrain has played a significant role for better mobility and stability of WMR. In this study, a diagonal recurrent neural network-based adaptive method is proposed to identify terrain parameters by the platform of a single driving wheel. According to the classical terramechanics model of wheel–soil interaction, a decoupling simplification model is developed by closed-form analytical equations. Five unknown terrain parameters are divided into two groups and included in two complex nonlinear equations. These parameters are used to compute the model outputs of force and torque of wheel–soil interaction. Dynamic back propagation algorithm is applied to update these parameters for compensating the errors between the prediction of neural network and measurable data in real time. The results of simulation show that the terrain parameters can be obtained and approximate the experimental value of terrain parameters when the predictive errors converge to zero.

[1]  Chee Kheong Siew,et al.  Real-time learning capability of neural networks , 2006, IEEE Trans. Neural Networks.

[2]  Simon Haykin,et al.  Neural Networks and Learning Machines , 2010 .

[3]  David Wettergreen,et al.  Motion Analysis System for Robot Traction Device Evaluation and Design , 2012, FSR.

[4]  Guangjun Liu,et al.  Interaction Mechanics Model for Rigid Driving Wheels of Planetary Rovers Moving on Sandy Terrain with Consideration of Multiple Physical Effects , 2015, J. Field Robotics.

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

[6]  D. Yu,et al.  Adaptation of diagonal recurrent neural network model , 2005, Neural Computing & Applications.

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

[8]  Paris A. Mastorocostas,et al.  A block-diagonal recurrent fuzzy neural network for system identification , 2009, Neural Computing and Applications.

[9]  DingLiang,et al.  Interaction Mechanics Model for Rigid Driving Wheels of Planetary Rovers Moving on Sandy Terrain with Consideration of Multiple Physical Effects , 2015 .

[10]  Chenguang Yang,et al.  Neural Network-Based Motion Control of an Underactuated Wheeled Inverted Pendulum Model , 2014, IEEE Transactions on Neural Networks and Learning Systems.

[11]  Michael Y. Hu,et al.  Forecasting with artificial neural networks: The state of the art , 1997 .

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

[13]  Zongben Xu,et al.  Approximation capability of interpolation neural networks , 2010, Neurocomputing.

[14]  Laura E. Ray,et al.  Estimation of net traction for differential-steered wheeled robots , 2009 .

[15]  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.

[16]  Yingchun Wang,et al.  State estimation of recurrent neural networks with interval time-varying delay: an improved delay-dependent approach , 2012, Neural Computing and Applications.

[17]  K. Iagnemma,et al.  Terramechanics Modeling of Mars Surface Exploration Rovers for Simulation and Parameter Estimation , 2011 .

[18]  Chenguang Yang,et al.  Neural-Adaptive Output Feedback Control of a Class of Transportation Vehicles Based on Wheeled Inverted Pendulum Models , 2012, IEEE Transactions on Control Systems Technology.

[19]  Dianhui Wang,et al.  Global Convergence of Online BP Training With Dynamic Learning Rate , 2012, IEEE Transactions on Neural Networks and Learning Systems.

[20]  Frank L. Lewis,et al.  Adaptive Optimal Control of Unknown Constrained-Input Systems Using Policy Iteration and Neural Networks , 2013, IEEE Transactions on Neural Networks and Learning Systems.

[21]  Bong-Jin Yum,et al.  Artificial neural network based approach for dynamic parameter design , 2011, Expert Syst. Appl..