CarSpeedNet: Learning-Based Speed Estimation from Accelerometer-Only Inertial Sensing

TL;DR

CarSpeedNet is a novel learning-based framework that estimates vehicle speed solely from smartphone accelerometer data, addressing sensor sparsity issues in low-cost or degraded scenarios without relying on traditional sensors.

Contribution

It introduces a deep learning approach to infer vehicle speed directly from raw accelerometer signals, bypassing the need for gyroscopes, odometry, or external positioning.

Findings

Achieves accurate speed estimation using only accelerometer data.

Handles sensor failure and drift scenarios effectively.

Outperforms traditional integration-based methods in sparse sensing conditions.

Abstract

Velocity estimation is a core component of state estimation and sensor fusion pipelines in mobile robotics and autonomous ground systems, directly affecting navigation accuracy, control stability, and operational safety. In conventional systems, velocity is obtained through wheel encoders, inertial navigation units, or tightly coupled multi-sensor fusion architectures. However, these sensing configurations are not always available or reliable, particularly in low-cost, redundancy-constrained, or degraded operational scenarios where sensors may fail, drift, or become temporarily unavailable. This paper investigates the feasibility of estimating vehicle speed using only a single low-cost inertial sensor: a three-axis accelerometer embedded in a commodity smartphone. We present CarSpeedNet, a learning-based inertial estimation framework designed to infer speed directly from raw accelerometer measurements, without access to gyroscopes, wheel odometry, vehicle bus data, or external positioning during inference. From a sensor fusion perspective, this setting represents an extreme case of sensing sparsity, in which classical integration-based or filter-based approaches become unstable due to bias accumulation and partial observability. Rather than explicitly estimating physical states such as orientation or sensor bias, the proposed approach performs implicit latent-state approximation from temporal accelerometer data.