Assessing e-scooters safety and drivability: a quantitative analysis

Leoni, Jessica; Tanelli, Mara; Strada, Silvia; Savaresi, Sergio M.

doi:10.1016/j.ifacol.2022.10.294

Cited by 6 publications

(3 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…If the classes are imbalanced, only considering the accuracy might give false outcomes [42]. Precision is the number of correctly predicted positives out of the predicted positives, as shown in (8). In order to avoid false positives, a precision metric can be used.…”

Section: False Positive True Negativementioning

confidence: 99%

See 1 more Smart Citation

Mixed Learning- and Model-Based Mass Estimation of Heavy Vehicles

İşbitirici,

Giarré,

Falcone

2024

Vehicles

View full text Add to dashboard Cite

This research utilized long short-term memory (LSTM) to oversee an RLS-based mass estimator based on longitudinal vehicle dynamics for heavy-duty vehicles (HDVs) instead of using the predefined rules. A multilayer LSTM network that analyzed parameters such as vehicle speed, longitudinal acceleration, engine torque, engine speed, and estimated mass from the RLS mass estimator was employed as the supervision method. The supervisory LSTM network was trained offline to recognize when the vehicle was operated so that the RLS estimator gave an estimate with the desired accuracy and the network was used as a reliability flag. High-fidelity simulation software was employed to collect data used to train and test the network. A threshold on the error percentage of the RLS mass estimator was used by the network to check the reliability of the algorithm. The preliminary findings indicate that the reliability of the RLS mass estimator could be predicted by using the LSTM network.

show abstract

Section: False Positive True Negativementioning

confidence: 99%

“…Fifteen fully connected layers, with a total of 1051 neurons, were used to estimate the mass. The authors in [8] employed a random forest algorithm to categorize the weight of e-scooter users. The preference for categorization over regression arises due to the scarcity of accessible data.…”

Section: Introductionmentioning

confidence: 99%

Mixed Learning- and Model-Based Mass Estimation of Heavy Vehicles

İşbitirici,

Giarré,

Falcone

2024

Vehicles

View full text Add to dashboard Cite

show abstract

“…Such an approach provides the mean and variance of the mass estimate. The work in [16] proposes a Random Forest method for mass estimation of passenger weight on e-scooters. The algorithm is used for classification rather than regression since there are limited data.…”

Section: Introductionmentioning

confidence: 99%

LSTM-Based Virtual Load Sensor for Heavy-Duty Vehicles

İşbitirici,

Giarré,

et al. 2023

Sensors

View full text Add to dashboard Cite

In this paper, a special recurrent neural network (RNN) called Long Short-Term Memory (LSTM) is used to design a virtual load sensor that estimates the mass of heavy vehicles. The estimation algorithm consists of a two-layer LSTM network. The network estimates vehicle mass based on vehicle speed, longitudinal acceleration, engine speed, engine torque, and accelerator pedal position. The network is trained and tested with a data set collected in a high-fidelity simulation environment called Truckmaker. The training data are generated in acceleration maneuvers across a range of speeds, while the test data are obtained by simulating the vehicle in the Worldwide harmonized Light vehicles Test Cycle (WLTC). Preliminary results show that, with the proposed approach, heavy-vehicle mass can be estimated as accurately as commercial load sensors across a range of load mass as wide as four tons.

show abstract

Statistical Analysis of the Vibrations Transmitted From an Electric Kick Scooter to Riders

Vella,

Digo,

Gastaldi

et al. 2024

Exp Tech

View full text Add to dashboard Cite

In recent years, micro-vehicles have been increasingly involved in urban mobility following the actual trend towards light, more affordable, and eco-friendly means of transportation. Among this vehicle category, the electric kick scooters (e-scooters) represent the most popular example driven by app-based sharing mobility services. Despite the positive implications, poor safety requirements and issues of discomfort are also related to this new segment. The recent spread of e-scooters is motivating the scientific community in investigating performance and ride comfort, in the attempt of improving vehicle design and safety regulations. The aim of this study is to evaluate e-scooter vibrations in driving in a realistic environment, constituted by bike path with seven speed bumps. Fourteen healthy young participants (seven males and seven females) are asked to conduct the test at two different constant velocities ($$5$$ 5 km/h and $$25$$ 25 km/h). Accelerations are acquired at the main human body segments as well as on the e-scooter. The assessment is based on identifying maxima and root mean squares from signal time histories. A non-parametrical statistical analysis is performed focusing on vibrations transmitted from vehicle to human body, e-scooter velocity, and some rider’s characteristics such as gender, mass, dominant arm, and dominant foot. Root mean squares and tests at low velocity generally underline a larger number of significant differences. Moreover, the parameter which mostly influences the system is the rider’s mass. Overall, the proposed methodology proves to be an efficient tool to investigate the vehicle-rider vibrational influence.

show abstract

Assessing e-scooters safety and drivability: a quantitative analysis

Cited by 6 publications

References 9 publications

Mixed Learning- and Model-Based Mass Estimation of Heavy Vehicles

Mixed Learning- and Model-Based Mass Estimation of Heavy Vehicles

LSTM-Based Virtual Load Sensor for Heavy-Duty Vehicles

Statistical Analysis of the Vibrations Transmitted From an Electric Kick Scooter to Riders

Contact Info

Product

Resources

About