AbolDeepIO: A Novel Deep Inertial Odometry Network for Autonomous Vehicles

Inertial measurement units (IMUs) suffer from bias and measurement noise, which makes it much more complicated to tackle the problem of inertial odometry (IO). Due to the error propagation over time, while estimating robot position, an inaccurate estimation or a small error will cause the odometry and a localization system unreliable and unusable in a split of seconds. This paper presents a novel triple-channel deep IO network architecture based on the physical and mathematical models of IMUs. The proposed method simulates the noise model in the training phase and becomes robust to noise during testing. Besides, the proposed network architecture also considers the time interval between two consecutive IMU readings (sampling time) so that it is robust to the change of IMU frequency and the missing of IMU information. To the best of our knowledge, this paper is the first work reviewing and analyzing the existing IO methods used by the deep-learning-based visual-IO approaches. The proposed network architecture outperforms all the existing solutions on the IMU readings of the challenging Micro Aerial Vehicle dataset and improves the accuracy by approximately 25%.

[1]  P. Savage.  Strapdown Inertial Navigation Integration Algorithm Design Part 1: Attitude Algorithms , 1998 .

[2]  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).

[3]  Gerhard P. Hancke,et al.  Pose Estimation of a Mobile Robot Based on Fusion of IMU Data and Vision Data Using an Extended Kalman Filter , 2017, Sensors.

[4]  Yi Lin,et al.  Autonomous aerial navigation using monocular visual‐inertial fusion , 2018, J. Field Robotics.

[5]  Hamid Reza Pourreza,et al.  Kinect Depth Recovery Based on Local Filters and Plane Primitives , 2017 .

[6]  Eric Foxlin,et al.  Pedestrian tracking with shoe-mounted inertial sensors , 2005, IEEE Computer Graphics and Applications.

[7]  Xiaoji Niu,et al.  Analysis and Modeling of Inertial Sensors Using Allan Variance , 2008, IEEE Transactions on Instrumentation and Measurement.

[8]  Raja Ariffin Raja Ghazilla,et al.  Reviews on Various Inertial Measurement Unit (IMU) Sensor Applications , 2013, SiPS 2013.

[9]  M. Petovello.  Real-time integration of a tactical-grade IMU and GPS for high-accuracy positioning and navigation , 2003 .

[10]  Arno Solin,et al.  Inertial Odometry on Handheld Smartphones , 2017, 2018 21st International Conference on Information Fusion (FUSION).

[11]  Isaac Skog,et al.  Cooperative localization by dual foot-mounted inertial sensors and inter-agent ranging , 2013, EURASIP J. Adv. Signal Process..

[12]  Yuan Yu,et al.  TensorFlow: A system for large-scale machine learning , 2016, OSDI.

[13]  Roland Siegwart,et al.  The EuRoC micro aerial vehicle datasets , 2016, Int. J. Robotics Res..

[14]  Fei-Fei Li,et al.  Large-Scale Video Classification with Convolutional Neural Networks , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[15]  Sen Wang,et al.  VINet: Visual-Inertial Odometry as a Sequence-to-Sequence Learning Problem , 2017, AAAI.

[16]  Eckehard Steinbach,et al.  Graph-based data fusion of pedometer and WiFi measurements for mobile indoor positioning , 2014, UbiComp.

[17]  Ahad Harati,et al.  Parallel RANSAC: Speeding up plane extraction in RGBD image sequences using GPU , 2015, 2015 5th International Conference on Computer and Knowledge Engineering (ICCKE).

[18]  Agathoniki Trigoni,et al.  Lightweight map matching for indoor localisation using conditional random fields , 2014, IPSN-14 Proceedings of the 13th International Symposium on Information Processing in Sensor Networks.

[19]  Agathoniki Trigoni,et al.  IONet: Learning to Cure the Curse of Drift in Inertial Odometry , 2018, AAAI.

[20]  Sen Wang,et al.  VidLoc: A Deep Spatio-Temporal Model for 6-DoF Video-Clip Relocalization , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[21]  Luc Van Gool,et al.  End-to-End Learning of Driving Models with Surround-View Cameras and Route Planners , 2018, ECCV.

[22]  Jie Liu,et al.  A realistic evaluation and comparison of indoor location technologies: experiences and lessons learned , 2015, IPSN.

[23]  Roland Siegwart,et al.  Robust visual inertial odometry using a direct EKF-based approach , 2015, IROS 2015.

[24]  William Whittaker,et al.  Autonomous driving in urban environments: Boss and the Urban Challenge , 2008, J. Field Robotics.

[25]  Daniel Cremers,et al.  Stereo DSO: Large-Scale Direct Sparse Visual Odometry with Stereo Cameras , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[26]  Denis Pomorski,et al.  GPS/IMU data fusion using multisensor Kalman filtering: introduction of contextual aspects , 2006, Inf. Fusion.

[27]  M. Westoby,et al.  ‘Structure-from-Motion’ photogrammetry: A low-cost, effective tool for geoscience applications , 2012 .

[28]  Jörg Stückler,et al.  Direct visual-inertial odometry with stereo cameras , 2016, 2016 IEEE International Conference on Robotics and Automation (ICRA).

[29]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[30]  Michael Bosse,et al.  Keyframe-based visual–inertial odometry using nonlinear optimization , 2015, Int. J. Robotics Res..

[31]  Jonathan Kelly,et al.  LSTM-Based Zero-Velocity Detection for Robust Inertial Navigation , 2018, 2018 International Conference on Indoor Positioning and Indoor Navigation (IPIN).

[32]  Isaac Skog,et al.  Evaluation of zero-velocity detectors for foot-mounted inertial navigation systems , 2010, 2010 International Conference on Indoor Positioning and Indoor Navigation.

[33]  John-Olof Nilsson,et al.  Foot-mounted inertial navigation made easy , 2014, 2014 International Conference on Indoor Positioning and Indoor Navigation (IPIN).

[34]  Juan D. Tardós,et al.  ORB-SLAM2: An Open-Source SLAM System for Monocular, Stereo, and RGB-D Cameras , 2016, IEEE Transactions on Robotics.

[35]  Jayant Murthy,et al.  Noise modeling and analysis of an IMU-based attitude sensor: improvement of performance by filtering and sensor fusion , 2016, Astronomical Telescopes + Instrumentation.