Comparative Study of Different Methods in Vibration-Based Terrain Classification for Wheeled Robots with Shock Absorbers

Autonomous robots that operate in the field can enhance their security and efficiency by accurate terrain classification, which can be realized by means of robot-terrain interaction-generated vibration signals. In this paper, we explore the vibration-based terrain classification (VTC), in particular for a wheeled robot with shock absorbers. Because the vibration sensors are usually mounted on the main body of the robot, the vibration signals are dampened significantly, which results in the vibration signals collected on different terrains being more difficult to discriminate. Hence, the existing VTC methods applied to a robot with shock absorbers may degrade. The contributions are two-fold: (1) Several experiments are conducted to exhibit the performance of the existing feature-engineering and feature-learning classification methods; and (2) According to the long short-term memory (LSTM) network, we propose a one-dimensional convolutional LSTM (1DCL)-based VTC method to learn both spatial and temporal characteristics of the dampened vibration signals. The experiment results demonstrate that: (1) The feature-engineering methods, which are efficient in VTC of the robot without shock absorbers, are not so accurate in our project; meanwhile, the feature-learning methods are better choices; and (2) The 1DCL-based VTC method outperforms the conventional methods with an accuracy of 80.18%, which exceeds the second method (LSTM) by 8.23%.

[1]  Karl Iagnemma,et al.  Unsupervised classification of slip events for planetary exploration rovers , 2017 .

[2]  Andreas Zell,et al.  Adaptive bayesian filtering for vibration-based terrain classification , 2009, 2009 IEEE International Conference on Robotics and Automation.

[3]  Jian Yang,et al.  Assessment of GF-3 Polarimetric SAR Data for Physical Scattering Mechanism Analysis and Terrain Classification , 2017, Sensors.

[4]  Jasper Snoek,et al.  Practical Bayesian Optimization of Machine Learning Algorithms , 2012, NIPS.

[5]  Jindong Liu,et al.  Surface classification based on vibration on omni-wheel mobile base , 2015, 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[6]  Lei Shi,et al.  Two-Stage Road Terrain Identification Approach for Land Vehicles Using Feature-Based and Markov Random Field Algorithm , 2018, IEEE Intelligent Systems.

[7]  Karl Iagnemma,et al.  Terrain classification and identification of tree stems using ground‐based LiDAR , 2012, J. Field Robotics.

[8]  Liang Lu,et al.  Terrain surface classification for autonomous ground vehicles using a 2D laser stripe-based structured light sensor , 2009, 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[9]  K. Walas.  Terrain Classification and Negotiation with a Walking Robot , 2015, J. Intell. Robotic Syst..

[10]  Wolfram Burgard,et al.  Deep spatiotemporal models for robust proprioceptive terrain classification , 2017, Int. J. Robotics Res..

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

[12]  Junqiang Xi,et al.  Self‐supervised learning to visually detect terrain surfaces for autonomous robots operating in forested terrain , 2012, J. Field Robotics.

[13]  Kai Zhao,et al.  A New Terrain Classification Framework Using Proprioceptive Sensors for Mobile Robots , 2017 .

[14]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[15]  Xu Zhao,et al.  Study of the Navigation Method for a Snake Robot Based on the Kinematics Model with MEMS IMU , 2018, Sensors.

[16]  Gregory Dudek,et al.  Autonomous gait selection for energy efficient walking , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[17]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1995, EuroCOLT.

[18]  Erkan Besdok,et al.  A Comparison of RBF Neural Network Training Algorithms for Inertial Sensor Based Terrain Classification , 2009, Sensors.

[19]  Andreas Zell,et al.  Recurrent Neural Networks for fast and robust vibration-based ground classification on mobile robots , 2016, 2016 IEEE International Conference on Robotics and Automation (ICRA).

[20]  David R. Bull,et al.  Terrain Classification From Body-Mounted Cameras During Human Locomotion , 2015, IEEE Transactions on Cybernetics.

[21]  Ingemar J. Cox,et al.  Autonomous Robot Vehicles , 1990, Springer New York.

[22]  Takashi Kubota,et al.  Autonomous Terrain Classification With Co- and Self-Training Approach , 2016, IEEE Robotics and Automation Letters.

[23]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

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

[25]  ZhiQiang Chen,et al.  Gearbox Fault Identification and Classification with Convolutional Neural Networks , 2015 .

[26]  Karl Iagnemma,et al.  DeepTerramechanics: Terrain Classification and Slip Estimation for Ground Robots via Deep Learning , 2018, ArXiv.

[27]  Paul Filitchkin,et al.  Feature-based terrain classification for LittleDog , 2012, 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[28]  Moncef Gabbouj,et al.  Real-Time Motor Fault Detection by 1-D Convolutional Neural Networks , 2016, IEEE Transactions on Industrial Electronics.

[29]  Moncef Gabbouj,et al.  Real-time vibration-based structural damage detection using one-dimensional convolutional neural networks , 2017 .

[30]  Andreas Zell,et al.  High resolution visual terrain classification for outdoor robots , 2011, 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops).

[31]  Jacobo Sandoval-Gutierrez,et al.  Robust Switched Tracking Control for Wheeled Mobile Robots Considering the Actuators and Drivers , 2018, Sensors.

[32]  Karl Iagnemma,et al.  Slippage estimation and compensation for planetary exploration rovers. State of the art and future challenges , 2018, J. Field Robotics.

[33]  Anthony Stentz,et al.  Using sound to classify vehicle-terrain interactions in outdoor environments , 2012, 2012 IEEE International Conference on Robotics and Automation.

[34]  Andreas Zell,et al.  Visual terrain classification by flying robots , 2012, 2012 IEEE International Conference on Robotics and Automation.

[35]  Christopher Assad,et al.  Unmanned ground vehicle perception using thermal infrared cameras , 2011, Defense + Commercial Sensing.

[36]  Andreas Zell,et al.  Comparison of Different Approaches to Vibration-based Terrain Classification , 2007, EMCR.

[37]  Lihua Xie,et al.  Comparison of different approaches to visual terrain classification for outdoor mobile robots , 2014, Pattern Recognit. Lett..

[38]  Chao Ma,et al.  Superpixel Segmentation Based Synthetic Classifications with Clear Boundary Information for a Legged Robot , 2018, Sensors.

[39]  Binh P. Nguyen,et al.  Robust Biometric Recognition From Palm Depth Images for Gloved Hands , 2015, IEEE Transactions on Human-Machine Systems.

[40]  Roland Siegwart,et al.  Haptic terrain classification for legged robots , 2010, 2010 IEEE International Conference on Robotics and Automation.

[41]  Afsar Saranli,et al.  Acoustic surface perception from naturally occurring step sounds of a dexterous hexapod robot , 2013 .

[42]  Navinda Kottege,et al.  Acoustics based terrain classification for legged robots , 2016, 2016 IEEE International Conference on Robotics and Automation (ICRA).

[43]  Wei-Yin Loh,et al.  Classification and regression trees , 2011, WIREs Data Mining Knowl. Discov..

[44]  Yan Chen,et al.  Energy Management and Driving Strategy for In-Wheel Motor Electric Ground Vehicles With Terrain Profile Preview , 2014, IEEE Transactions on Industrial Informatics.

[45]  Larry H. Matthies,et al.  Terrain Adaptive Navigation for planetary rovers , 2009, J. Field Robotics.

[46]  Yiming Yang,et al.  A re-examination of text categorization methods , 1999, SIGIR '99.

[47]  Pedro M. Domingos,et al.  On the Optimality of the Simple Bayesian Classifier under Zero-One Loss , 1997, Machine Learning.

[48]  Duncan W. Haldane,et al.  Performance analysis and terrain classification for a legged robot over rough terrain , 2012, 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[49]  Prithviraj Dasgupta,et al.  Ensemble Learning With Weak Classifiers for Fast and Reliable Unknown Terrain Classification Using Mobile Robots , 2017, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[50]  Steven Verstockt,et al.  Convolutional Neural Network Based Fault Detection for Rotating Machinery , 2016 .

[51]  Steven Dubowsky,et al.  Traction Control of Wheeled Robotic Vehicles in Rough Terrain with Application to Planetary Rovers , 2004, Int. J. Robotics Res..

[52]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[53]  Sanjay Ranka,et al.  An Efficient Deep Representation Based Framework for Large-Scale Terrain Classification , 2018, 2018 24th International Conference on Pattern Recognition (ICPR).

[54]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[55]  Mark R. Cutkosky,et al.  Integrated Ground Reaction Force Sensing and Terrain Classification for Small Legged Robots , 2016, IEEE Robotics and Automation Letters.

[56]  Chee Kheong Siew,et al.  Extreme learning machine: Theory and applications , 2006, Neurocomputing.

[57]  Matej Hoffmann,et al.  The effect of motor action and different sensory modalities on terrain classification in a quadruped robot running with multiple gaits , 2014, Robotics Auton. Syst..

[58]  Andreas Zell,et al.  Vibration-based Terrain Classification Using Support Vector Machines , 2006, 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[59]  Qiang Chen,et al.  Network In Network , 2013, ICLR.

[60]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.