A Non-Invasive Method for the Safe Interaction of Cities and Electric Vehicle Fleets
Bill Power, Brian Mulkeene, Anthony D. Fagan, Robert Shorten

TL;DR
This paper proposes a non-invasive audio-based detection system for electric vehicles, enhancing pedestrian safety in cities by alerting them to EVs' presence through high-frequency sound emissions.
Contribution
It introduces a novel method leveraging high-frequency audio emissions from EVs for safe detection, validated through experimental testing on multiple vehicles.
Findings
Successful detection of EVs using high-frequency audio signals
Experimental validation with four different test vehicles
Preliminary EV detection algorithm demonstrated effectiveness
Abstract
Electric and hybrid vehicles are growing in popularity. While these vehicles produce less pollution, they also produce less audible noise, especially at lower speeds. This makes it harder for pedestrians and cyclists to detect an approaching vehicle. Thus, an additional system is required to detect electric and hybrid vehicles and alert pedestrians and cyclists of their whereabouts, especially while these vehicles are driving at low speeds in cities. This paper introduces one such method based on high frequency audio emissions that are present in EVs, which arise, for example, from the process of magnetostriction. Our method is tested experimentally using 4 different tests vehicles, and a preliminary EV detection algorithm is also presented.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
