# Learning Car Speed Using Inertial Sensors for Dead Reckoning Navigation

arXiv: https://arxiv.org/abs/2205.07883 · HTML: https://mlsanity.com/paper/2205.07883/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 20 references that are in the map.
- First posted on arXiv 15 May 2022.

## Builds on (most cited first, 4 of 4)

- [Self-Driving Cars: A Survey](https://mlsanity.com/paper/1901.04407/) (2019)
- [RINS-W: Robust Inertial Navigation System on Wheels](https://mlsanity.com/paper/1903.02210/) (2019)
- [Deep Learning Based Speed Estimation for Constraining Strapdown Inertial Navigation on Smartphones](https://mlsanity.com/paper/1808.03485/) (2018)
- [End-to-End Velocity Estimation For Autonomous Racing](https://mlsanity.com/paper/2003.06917/) (2020)

## Built on by (most cited first, 7 of 7)

- [Inertial Navigation Meets Deep Learning: A Survey of Current Trends and Future Directions](https://mlsanity.com/paper/2307.00014/) (2023)
- [Deep Learning for Inertial Sensor Alignment](https://mlsanity.com/paper/2212.11120/) (2022)
- [Surface Recognition for e-Scooter Using Smartphone IMU Sensor](https://mlsanity.com/paper/2302.12720/) (2023)
- [Learning Position From Vehicle Vibration Using an Inertial Measurement Unit](https://mlsanity.com/paper/2303.03942/) (2023)
- [Learning-Based Speed Estimation from Accelerometer-Only Inertial Sensing](https://mlsanity.com/paper/2401.07468/) (2024)
- [Improving Requirements Classification with SMOTE-Tomek Preprocessing](https://mlsanity.com/paper/2501.06491/) (2025)
- [Can Predicted Dynamics Exist in the Physical World?](https://mlsanity.com/paper/2606.00089/) (2026)

## Abstract (arXiv)

A deep neural network (DNN) is trained to estimate the speed of a car driving in an urban area using as input a stream of measurements from a low-cost six-axis inertial measurement unit (IMU). Three hours of data was collected by driving through the city of Ashdod, Israel in a car equipped with a global navigation satellite system (GNSS) real time kinematic (RTK) positioning device and a synchronized IMU. Ground truth labels for the car speed were calculated using the position measurements obtained at the high rate of 50 Hz. A DNN architecture with long short-term memory layers is proposed to enable high-frequency speed estimation that accounts for previous inputs history and the nonlinear relation between speed, acceleration and angular velocity. A simplified aided dead reckoning localization scheme is formulated to assess the trained model which provides the speed pseudo-measurement. The trained model is shown to substantially improve the position accuracy during a 4 minutes drive without the use of GNSS position updates.