Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Surface Recognition for e-Scooter Using Smartphone IMU Sensor

Areej Eweida, Nimord Segol, Maxim Freydin, Niv Sfaradi, Barak Or

TL;DR

A data-driven method is proposed to recognize when an e-scooter is on a road or a sidewalk, using only the widely available inertial measurement unit (IMU) sensors on a smartphone device.

Abstract

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.

Surface Recognition for e-Scooter Using Smartphone IMU Sensor

TL;DR

A data-driven method is proposed to recognize when an e-scooter is on a road or a sidewalk, using only the widely available inertial measurement unit (IMU) sensors on a smartphone device.

Abstract

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.
Paper Structure (16 sections, 2 equations, 4 figures, 1 table)

This paper contains 16 sections, 2 equations, 4 figures, 1 table.

Table of Contents

  1. Introduction
  2. Data set creation
  3. Raw data collection
  4. Pre-processing
  5. Data generation
  6. Classifiers
  7. Models
  8. DNNs loss function and training hyperparameters
  9. Loss function for DNN-based models
  10. Training DNN-based models
  11. Results
  12. Evaluation Metrics
  13. Best performing model
  14. The performance of classical models
  15. Field experiment
  16. ...and 1 more sections

Figures (4)

  • Figure 1: Left: an example of a street with both sidewalk and an asphalt road. Right: a smartphone device mounted on a scooter. Note the device frame of reference.
  • Figure 2: Schematic description of the dataset generation process.
  • Figure 3: DNN architecture: LSTM, two convolutional layers are followed by one dense layer with a connecting average-pooling layer. Finally, a linear layer eventually outputs the probability of getting each one of the classes.
  • Figure 4: Results of the selected classifier on a route containing both sidewalk and road.