GALNet: An End-to-End Deep Neural Network for Ground Localization of Autonomous Cars

: Odometry based on Inertial, Dynamic and Kinematic data (IDK-Odometry) for autonomous cars has been widely used to compute the prior estimation of Bayesian localization systems which fuse other sensors such as camera, RADAR or LIDAR. IDK-Odometry also gives the vehicle information by way of emergency when other methods are not available. In this work, we propose the use of deep neural networks to estimate the relative pose of the car given two timestamps of inertial-dynamic-kinematic data. We show that a neural network can find a solution to the optimization problem employing an approximation of the Vehicle Slip Angle (VSA). We compared our results to an IDK-Odometry system based on an Unscented Kalman Filter and Ackermann-wheel odometry. To train and test the network, we used a dataset which consists of ten driven trajectories with our autonomous car. Moreover, we successfully improved the results of the network employing collected data with a model autonomous car in order to increase the trajectories with high VSA.

[1]  Arnaud de La Fortelle,et al.  Deep Sensor Fusion for Real-Time Odometry Estimation , 2019, 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[2]  Martin Brossard,et al.  Learning Wheel Odometry and IMU Errors for Localization , 2019, 2019 International Conference on Robotics and Automation (ICRA).

[3]  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.

[4]  Ahmed Tamtaoui,et al.  Improving low cost sensor based vehicle positioning with Machine Learning , 2018 .

[5]  Ian D. Reid,et al.  Unsupervised Learning of Monocular Depth Estimation and Visual Odometry with Deep Feature Reconstruction , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[6]  Marco Gadola,et al.  On the vehicle sideslip angle estimation: a literature review of methods, models and innovations , 2018 .

[7]  Massimiliano Magnani,et al.  A novel calibration method for industrial AGVs , 2017, Robotics Auton. Syst..

[8]  Sen Wang,et al.  DeepVO: Towards end-to-end visual odometry with deep Recurrent Convolutional Neural Networks , 2017, 2017 IEEE International Conference on Robotics and Automation (ICRA).

[9]  Seongjin Yim,et al.  Coordinated control of ESC and AFS with adaptive algorithms , 2017 .

[10]  Bei Shaoyi,et al.  Vehicle Sideslip Angle Estimation Based on General Regression Neural Network , 2016 .

[11]  Hamid M. Lankarani,et al.  Hybrid simulation of a dynamic multibody vehicle suspension system using neural network modeling fit of tire data , 2016 .

[12]  Zhen Liu,et al.  Unscented Kalman Filter-Trained Neural Networks for Slip Model Prediction , 2016, PloS one.

[13]  Roberto Cipolla,et al.  Convolutional networks for real-time 6-DOF camera relocalization , 2015, ArXiv.

[14]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[15]  Wolfram Burgard,et al.  A benchmark for the evaluation of RGB-D SLAM systems , 2012, 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[16]  Kevin L. Moore,et al.  Pose estimation of Ackerman steering vehicles for outdoors autonomous navigation , 2010, 2010 IEEE International Conference on Industrial Technology.

[17]  Kazuya Yoshida,et al.  Odometry Correction Using Visual Slip Angle Estimation for Planetary Exploration Rovers , 2010, Adv. Robotics.

[18]  John Y. Hung,et al.  An adaptive non-linear state estimator for vehicle lateral dynamics , 2009, 2009 35th Annual Conference of IEEE Industrial Electronics.

[19]  Jon Rigelsford,et al.  Automotive Control Systems: For Engine, Driveline and Vehicle , 2004 .

[20]  Hideaki Sasaki,et al.  A Side-Slip Angle Estimation Using Neural Network for a Wheeled Vehicle , 2000 .

[21]  Yoshiki Fukada,et al.  SLIP-ANGLE ESTIMATION FOR VEHICLE STABILITY CONTROL , 1999 .

[22]  Sepp Hochreiter,et al.  The Vanishing Gradient Problem During Learning Recurrent Neural Nets and Problem Solutions , 1998, Int. J. Uncertain. Fuzziness Knowl. Based Syst..

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

[24]  Peter Fejes,et al.  Estimation of Steering Wheel Angle in Heavy-Duty Trucks , 2016 .

[25]  Rolf Isermann,et al.  Cornering Stiffness and Sideslip Angle Estimation for Integrated Vehicle Dynamics Control , 2016 .

[26]  Roland Memisevic,et al.  Learning Visual Odometry with a Convolutional Network , 2015, VISAPP.

[27]  Thomas Moore,et al.  A Generalized Extended Kalman Filter Implementation for the Robot Operating System , 2014, IAS.

[28]  Moritz Diehl,et al.  Model Predictive Control of Autonomous Vehicles , 2014 .

[29]  Ferruccio Resta,et al.  Vehicle Sideslip Angle Estimation Through Neural Networks: Application to Numerical Data , 2006 .

[30]  U Kiencke and L Nielsen.  Automotive Control Systems: For Engine, Driveline, and Vehicle , 2000 .