Surface Recognition for e-Scooter Using Smartphone IMU Sensor

In recent years, as the use of micromobility gained popularity, technological challenges connected to e-scooters became increasingly important. This paper focuses on road surface recognition, an important task in this area. A reliable and accurate method for road surface recognition can help improve the safety and stability of the vehicle. Here a data-driven method is proposed to recognize if an e-scooter is on a road or a sidewalk. The proposed method uses only the widely available inertial measurement unit (IMU) sensors on a smartphone device. deep neural networks (DNNs) are used to infer whether an e-scooteris driving on a road or on a sidewalk by solving a binary classification problem. A data set is collected and several different deep models as well as classical machine learning approaches for the binary classification problem are applied and compared. Experiment results on a route containing the two surfaces are presented demonstrating the DNNs ability to distinguish between them.

[1]  M. Freydin,et al.  MountNet: Learning an Inertial Sensor Mounting Angle with Deep Neural Networks , 2022, ArXiv.

[2]  I. Klein,et al.  A Hybrid Model and Learning-Based Adaptive Navigation Filter , 2022, IEEE Transactions on Instrumentation and Measurement.

[3]  M. Freydin,et al.  Learning Car Speed Using Inertial Sensors for Dead Reckoning Navigation , 2022, IEEE Sensors Letters.

[4]  Kai Chen.  Road Roughness Recognition Based on Lidar , 2022, Journal of Physics: Conference Series.

[5]  S. Cafiso,et al.  Urban Road Pavements Monitoring and Assessment using Bike and E-scooter as probe vehicles , 2022, Case Studies in Construction Materials.

[6]  Matthias Springer,et al.  A Mobile and Modular Low-Cost Sensor System for Road Surface Recognition Using a Bicycle , 2020, 2020 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI).

[7]  Olegas Prentkovskis,et al.  Identification of Road-Surface Type Using Deep Neural Networks for Friction Coefficient Estimation , 2020, Sensors.

[8]  Li Liu,et al.  Abnormal Road Surface Recognition Based on Smartphone Acceleration Sensor , 2020, Sensors.

[9]  Hiroki Watanabe,et al.  Footsteps and inertial data-based road surface condition recognition method , 2019, MUM.

[10]  Shinpei Kato,et al.  Road Surface Condition Inspection Using a Laser Scanner Mounted on an Autonomous Driving Car , 2019, 2019 IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops).

[11]  Qi Shan,et al.  RIDI: Robust IMU Double Integration , 2017, ECCV.

[12]  Naohito Takasuka,et al.  Road Surface Recognition Using Laser Radar for Automatic Platooning , 2016, IEEE Transactions on Intelligent Transportation Systems.

[13]  Keiron O'Shea,et al.  An Introduction to Convolutional Neural Networks , 2015, ArXiv.

[14]  Edward Hoare,et al.  Analysis of classification algorithms applied to road surface recognition , 2015, 2015 IEEE Radar Conference (RadarCon).

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

[16]  L. Breiman.  Random Forests , 2001, Encyclopedia of Machine Learning and Data Mining.

[17]  S. Hochreiter,et al.  Long Short-Term Memory , 1997, Neural Computation.

[18]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[19]  M. Tanelli,et al.  Assessing e-scooters safety and drivability: a quantitative analysis , 2022, IFAC-PapersOnLine.

[20]  Ge Guo,et al.  Vehicle Localization During GPS Outages With Extended Kalman Filter and Deep Learning , 2021, IEEE Transactions on Instrumentation and Measurement.

[21]  Manuela Herman,et al.  Aided Navigation Gps With High Rate Sensors , 2016 .