MicroVision - Development, Testing, and Demonstration of a Real-Time Support System for Electric Vehicle Riders
Micro-mobility and the electrification of small vehicles is particularly promising from a sustainability perspective as it reduces the need to use larger vehicles for transportation. However, the increased popularity and notably the growing fleet of available shared e-scooters in urban areas has been accompanied by safety concerns regarding use and integration.
Background
Small electric vehicles have gained in popularity during recent years. In addition, transportation companies have adopted a new mode of operation that is based on sharing vehicles without docking stations. As the fleet continued to expand to satisfy an increasing demand, concerns regarding safety and integration were heard. Unsafe riding behavior is one of the observed safety issues[1] that has contributed to the recent ban of shared e-scooters in some large cities[2].
Goal
This project aims to develop a real-time, camera-based rider assistance safety system for e-scooters and e-bikes. The system will consist of low-cost sensors to increase availability. The goal is to promote safer interactions between road users in urban environments. The development involves gathering and annotation of image data focused on micro-mobility vehicles.
Method
The first steps of the development are data collection and annotation, along with training of machine learning models. We aim to repurpose state-of-the-art models for object detection as well as depth estimation. The models will eventually be integrated into a system and deployed to hardware for real-time testing on the target vehicle types. Finally, the functionality of the system will be demonstrated in a lab environment.
Utilization of results
The object detection dataset will be shared together with the retrained model weights. We believe that the sharing of research artifacts will promote further research into safety and sustainability of small electric vehicles. Our findings will be documented in a scientific paper. In addition, we aim to publish any novelties related to the depth estimation model.
[1] Gioldasis, C., Christoforou, Z., & Seidowsky, R. (2021). Risk-taking behaviors of e-scooter users: A survey in Paris. Accident Analysis & Prevention, 163, 106427. https://doi.org/10.1016/j.aap.2021.106427
[2] New York Times, 2023. https://www.nytimes.com/2023/04/03/world/europe/paris-electric-scooters-ban.html
Project period
September 2023 - August 2025
Contact
Da Wang, Autoliv
da.wang@autoliv.com
Partners
Autoliv, Chalmer University and SAFER participate as advisor.
Vinnova number
2023-01047
