The rapidly increasing popularity of micromobility devices, such as e-scooters and bicycles, in urban environments underscores the critical need for advanced trajectory prediction models to enhance road safety and facilitate seamless integration into intelligent transportation systems. This study introduces a novel approach to predicting the movements of bicyclists and e-scooter riders by leveraging a unique dataset that combines bird's-eye and egocentric views, collected from diverse urban settings across the United States. Employing state-of-the-art deep learning techniques, our model significantly outperforms traditional linear and polynomial regression models in terms of Average Displacement Error (ADE) and Final Displacement Error (FDE), demonstrating superior accuracy in forecasting the trajectories of vulnerable road users. Furthermore, our approach incorporates cognitive annotations to predict crossing intentions, enriching the model's predictive capabilities. The findings highlight the potential of our method to contribute to the development of proactive safety measures and collision avoidance systems, ultimately fostering safer urban mobility landscapes for all road users.
Intent-Guided Trajectory Prediction for E-Scooter Riders and Bicyclists
24.09.2024
4500531 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Improving Safety for Motorcycle, Scooter and Moped Riders
TIBKAT | 2015
|DOAJ | 2025
|Can you Park your Scooter There? Why Scooter Riders Mispark and What to do about it
DOAJ | 2021
|Gaze Behavior of E-Scooter Riders in an Urban Environment
Springer Verlag | 2024
|Case Study on the Traffic Collision Patterns of E-Scooter Riders
Transportation Research Record | 2023
|