Kinematic signatures of impairment: Detecting alcohol intoxication in e-scooter riders using sensor data and machine learning
Abstract
Alcohol intoxication is a leading contributor to fatal and severe-injured e-scooterist crashes. Current countermeasures, such as temporal restrictions or pre-ride cognitive screening, cannot continuously assess an e-scooterist's physical motor control or impairment in real time. We conducted a controlled experiment in which 25 participants rode an instrumented e-scooter through a test track while sober and at two targeted blood alcohol concentration levels (0.05% and 0.08%). The e-scooter was instrumented with a six-axis inertial measurement unit (IMU), and throttle and brake lever position sensors, all sampled at 100 Hz. Two complementary signal features were computed: normalised permutation entropy, which quantifies temporal complexity, and standard deviation, which quantifies signal amplitude. Repeated measures correlation identified seven kinematic features (all IMU and throttle signals) whose entropy decreased (p < 0.001) while standard deviation increased (p < 0.01) with increasing intoxication, indicating that intoxicated riders shift from continuous, low-amplitude micro-corrections to fewer, high-amplitude reactive corrections. An entropy based multi-class logistic regression classifier, evaluated through leave-one-participant-out cross-validation, achieved 85% overall accuracy and a weighted one-vs-rest area under the receiver operating characteristic curve (AuROC) of 0.94, with a sober-vs-high AuROC of 1.00. Steering rate and lateral acceleration were the most important predictive features, indicating that alcohol induces a distinct collapse in lateral equilibrium during riding. Ultimately, these results demonstrate that onboard kinematic sensing combined with entropy-based signal analysis can reliably distinguish sober from intoxicated e-scooter riding, providing a foundation for automatic intoxication detection systems that preserve mobility for sober riders.
Related
- Learning smooth dynamics via Kinematic Interpolants
- Investigating the Early Signatures of Feature Learning in Deep Linear Networks
- An Obukhov-Corrsin-Yaglom law for a kinematic model of turbulence
- Kinematic properties of the Pauli equation
- Flexible-body Modeling, Kinematic Identification, and Assembly Accuracy of Overconstrained Spatial Linkages
BibTeX
@misc{pai2026kinematic,
title = {{Kinematic signatures of impairment: Detecting alcohol intoxication in e-scooter riders using sensor data and machine learning}},
author = {Rahul Rajendra Pai and Marco Dozza and Alexander Rasch and Ali Mohammadi and Marco Capuccini},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.38276},
eprint = {2609.38276},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.38276},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - UNPB
TI - Kinematic signatures of impairment: Detecting alcohol intoxication in e-scooter riders using sensor data and machine learning
AU - Rahul Rajendra Pai
AU - Marco Dozza
AU - Alexander Rasch
AU - Ali Mohammadi
AU - Marco Capuccini
PY - 2026
DA - 2026/09/29
PB - arXiv
DO - 10.48550/arxiv.2609.38276
UR - https://arxiv.org/abs/2609.38276
AB - Alcohol intoxication is a leading contributor to fatal and severe-injured e-scooterist crashes. Current countermeasures, such as temporal restrictions or pre-ride cognitive screening, cannot continuously assess an e-scooterist's physical motor control or impairment in real time. We conducted a controlled experiment in which 25 participants rode an instrumented e-scooter through a test track while sober and at two targeted blood alcohol concentration levels (0.05% and 0.08%). The e-scooter was instrumented with a six-axis inertial measurement unit (IMU), and throttle and brake lever position sensors, all sampled at 100 Hz. Two complementary signal features were computed: normalised permutation entropy, which quantifies temporal complexity, and standard deviation, which quantifies signal amplitude. Repeated measures correlation identified seven kinematic features (all IMU and throttle signals) whose entropy decreased (p < 0.001) while standard deviation increased (p < 0.01) with increasing intoxication, indicating that intoxicated riders shift from continuous, low-amplitude micro-corrections to fewer, high-amplitude reactive corrections. An entropy based multi-class logistic regression classifier, evaluated through leave-one-participant-out cross-validation, achieved 85% overall accuracy and a weighted one-vs-rest area under the receiver operating characteristic curve (AuROC) of 0.94, with a sober-vs-high AuROC of 1.00. Steering rate and lateral acceleration were the most important predictive features, indicating that alcohol induces a distinct collapse in lateral equilibrium during riding. Ultimately, these results demonstrate that onboard kinematic sensing combined with entropy-based signal analysis can reliably distinguish sober from intoxicated e-scooter riding, providing a foundation for automatic intoxication detection systems that preserve mobility for sober riders.
ER -