Neural network based terramechanics modeling and estimation for deformable terrains

In this work, a neural network based terramechanics model and terrain estimator are presented with an outlook for optimal control applications such as model predictive control. Recognizing the limitations of the state-of-the-art terramechanics models in terms of operating conditions, computational cost, and continuous differentiability for gradient-based optimization, an efficient and twice continuously differentiable terramechanics model is developed using neural networks for dynamic operations on deformable terrains. It is demonstrated that the neural network terramechanics model is able to predict the lateral tire forces accurately and efficiently compared to the Soil Contact Model as a state-of-the-art model. Furthermore, the neural network terramechanics model is implemented within a terrain estimator and it is shown that using this model the estimator converges within around 2% of the true terrain parameter. Finally, with model predictive control applications in mind, which typically rely on bicycle models for their predictions, it is demonstrated that utilizing the estimated terrain parameter can reduce prediction errors of a bicycle model by orders of magnitude. The result is an efficient, dynamic, twice continuously differentiable terramechanics model and estimator that has inherent advantages for implementation in model predictive control as compared to previously established models.

[1]  Rudolph van der Merwe,et al.  The unscented Kalman filter for nonlinear estimation , 2000, Proceedings of the IEEE 2000 Adaptive Systems for Signal Processing, Communications, and Control Symposium (Cat. No.00EX373).

[2]  Bernd Schäfer,et al.  On the treatment of soft soil parameter uncertainties in planetary rover mobility simulations , 2016 .

[3]  Kazuya Yoshida,et al.  Terramechanics‐based model for steering maneuver of planetary exploration rovers on loose soil , 2007, J. Field Robotics.

[4]  Bjarne A. Foss,et al.  Constrained nonlinear state estimation based on the UKF approach , 2009, Comput. Chem. Eng..

[5]  Rainer Krenn,et al.  Soft Soil Contact Modeling Technique for Multi-Body System Simulation , 2011 .

[6]  Bernd Schäfer,et al.  Parameter Identification of a Planetary Rover Wheel-Soil Contact Model via a Bayesian Approach , 2014, J. Field Robotics.

[7]  Tianyou Guo Power Consumption Models for Tracked and Wheeled Small Unmanned Ground Vehicles on Deformable Terrains. , 2016 .

[8]  Tulga Ersal,et al.  Combined Speed and Steering Control in High-Speed Autonomous Ground Vehicles for Obstacle Avoidance Using Model Predictive Control , 2017, IEEE Transactions on Vehicular Technology.

[9]  Kshitij Jain,et al.  Online terrain estimation for autonomous vehicles on deformable terrains , 2019, ArXiv.

[10]  Hammad Mazhar,et al.  Chrono: An Open Source Multi-physics Dynamics Engine , 2015, HPCSE.

[11]  Gerd Hirzinger,et al.  SCM – A SOIL CONTACT MODEL FOR MULTI-BODY SYSTEM SIMULATIONS , 2009 .

[12]  Stratis Kanarachos,et al.  Tire lateral force estimation and grip potential identification using Neural Networks, Extended Kalman Filter, and Recursive Least Squares , 2018, Neural Computing and Applications.

[13]  Huei Peng,et al.  Fast computation of wheel-soil interactions for safe and efficient operation of mobile robots , 2011, 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[14]  Karl Iagnemma,et al.  Terrain Estimation Methods for Enhanced Autonomous Rover Mobility , 2006 .

[15]  Tulga Ersal,et al.  A nonlinear model predictive control formulation for obstacle avoidance in high-speed autonomous ground vehicles in unstructured environments , 2018 .

[16]  Nedjeljko Peric,et al.  Neural network based tire/road friction force estimation , 2008, Eng. Appl. Artif. Intell..

[17]  Steven Dubowsky,et al.  Terrain estimation for high-speed rough-terrain autonomous vehicle navigation , 2002, SPIE Defense + Commercial Sensing.

[18]  Eric J. Rossetter,et al.  Vehicle Sideslip and Roll Parameter Estimation using GPS , 2002 .

[19]  Andreas Zell,et al.  A combination of vision- and vibration-based terrain classification , 2008, 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[20]  Tulga Ersal,et al.  A study on model fidelity for model predictive control-based obstacle avoidance in high-speed autonomous ground vehicles , 2016 .

[21]  David Gorsich,et al.  A technical survey on Terramechanics models for tire–terrain interaction used in modeling and simulation of wheeled vehicles , 2015 .

[22]  Karl Iagnemma,et al.  Slippage and immobilization detection for planetary exploration rovers via machine learning and proprioceptive sensing , 2018, J. Field Robotics.

[23]  Hoyong Kim,et al.  A Tire Side Force Model by Artificial Neural Network , 1995 .

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

[25]  William Clarke Smith Modeling of Wheel-Soil Interaction for Small Ground Vehicles Operating on Granular Soil. , 2014 .