E-scooter operator Voi has launched the world’s first large scale pilot of computer vision on e-scooters. AI technology installed on the e-scooter can detect when it leaves the road and rides on a pavement, or when the vehicle is parked incorrectly.
Voi is working with Irish micromobility start-up Luna, whose technology offers real-time lane segmentation and pedestrian detection for scooters, similar to that available in high-end cars.
Voi e-scooters fitted with the new technology were tested on Stockholm streets today, in advance of deployment in the UK city of Northampton later this month. Voi has obtained a licence to operate in the city, as part of the British government’s national trial of e-scooters, which started last year and runs until spring 2022.
The trial aims to demonstrate the potential of the technology to increase the safety of e-scooters by fixing the problem of pavement riding. The technology will also provide tools to identify problem areas and adapt infrastructure for micromobility, by conveying real-time data about how the vehicles are being used.
The smart camera hardware and electronics have been honed by Luna and Voi over the past six months, to integrate with the latest Voi vehicles. The computer vision algorithms have been trained extensively using hours of video footage from Northampton.
Two phase pilot
Voi will initially install cameras on e-scooters in Northampton for a two-phase pilot starting this month. In the first phase, a controlled user group will road test the computer vision technology to collect real-time visual information on the environment the e-scooter is travelling through. It will also detect pedestrians in the path of the e-scooter. The technology can identify the surface that an e-scooter is travelling on, such as a bike lane, pavement, or roadway, and can alert the rider with an audible alarm if they are riding on the footpath.
In the second phase of the trial later in the summer, approximately 100 cameras will be installed on the publicly available scooter fleet in Northampton. In addition to the audible alert, this phase of the pilot will explore the potential to automatically slow scooters if inappropriate riding is detected on footpaths or in heavily pedestrianised areas.
Data from the pilot will be shared with the council so that it can collect a detailed record of how and where the e-scooters are being ridden. This will help Voi to correct bad behaviour and will give the city data-driven insights into e-scooter use and the interactions with other modes of transport and pedestrians. By 2022, Luna expects to be able to integrate its camera technology directly into the stem or handlebars of the e-scooters for rent.
“Computer vision e-scooters can be trained to see and recognise situations that are hazardous,” explains Fredrik Hjelm, co-founder and CEO of Voi Technology. “ This world-first pilot will set new standards of safety for this new form of transport. Having helped riders to take more than 60 million rides across Europe, we understand the issues involved in e-scooter safety and are always looking for ways to do better. We are very proud to be the first e-scooter operator to incorporate computer vision technology at scale for the benefit of our riders, pedestrians and authorities.”
“With this trial, we look forward to demonstrating how e-scooters equipped with computer vision can make a verifiable difference to rider compliance and sidewalk riding behaviour in cities,” adds Andrew Fleury, Luna co-founder & CEO. “We’ve noticed cities across the world requesting technological solutions to challenges like pavement riding and it’s fantastic to be working with such a safety conscious operator like Voi, to develop market-ready solutions. The value of the smart city data that can be generated by vision-equipped scooters is only beginning to be understood by micromobility stakeholders, and we’re excited to be exploring these early use cases with Voi.”
Improving e-scooter compliance
Voi will use the Luna technology to improve compliance, not just in terms of riding behaviour, but also in relation to proper parking. The Luna parking algorithm can spot if a scooter is positioned correctly in a ‘virtual dock’ by using a painted scooter logo or corral on the ground, or any other surrounding visual clues that it is trained to detect. Using the camera as a sensor, Luna can also help e-scooters to be parked with a level of accuracy that standard GPS technology cannot match.
Voi is committed to using innovation to ensure that every e-scooter ride is a responsible one, and every stationary e-scooter is a safe one. By collaborating with Luna, Voi will be able to build a record of where and how the scooters are being ridden and parked. Cities are expected to use the data to both understand poor rider behaviour and also to identify where infrastructure improvements to the public realm could help e-scooter riders and other road users.
By working in partnership with local councils and companies like Luna, Voi is dedicated to empowering people to leave their cars behind and move around their city in a safer, more sustainable way. The Luna technology will give authorities across Europe the confidence that they can have greater control over rental e-scooters, which provide a new carbon-neutral and socially distanced solution to urban travel.