The European electric scooter company Voi is turning to artificial intelligence to enable its vehicles to detect pedestrians and sidewalks. The startup hopes this move will ease chaotic micromobility concerns.
As e-scooter usage has surged throughout 2020, safety concerns have also increased around how the devices are used and deployed in busy cities. In response to those concerns, Voi plans to become the first company to deploy computer vision and on-device AI on scooters.
Voi, founded out of Sweden in 2018, is just one of many e-scooter startups that allow people to download a mobile app, find the nearest scooter, and pay for each minute that they need it. While the company only operates in Europe as of now, it has raised more than $250 million in VC investment in the past few years and achieved profitability for the first time this year.
The technology will help avert collisions and issue alerts if scooters are being used inappropriately or dangerously. Ultimately, it’s about using real-time knowledge to help electric scooters understand their environment.
In an interview with VentureBeat, Voi CEO Fredrik Hjelm said, “Voi is developing scooters that can ‘see’ what’s around them and therefore irrefutably ‘know’ what they need to do in order to be safe, whereas other scooters are trying to ‘feel’ what’s around them and use that to ‘guess’ what they should do next.”
Voi isn’t the first company to attempt using AI. Earlier in 2020, Lime announced plans to prevent sidewalk riding by “understanding” the underlying surface’s vibration. Lime, however, was only able to issue a warning after a rider was already on the sidewalk by crunching sensor data acquired from the speedometer and accelerometer. While California noted Lime was the only operation to make significant headway in preventing sidewalk riders, the inability to detect the activity in real-time made the technology less useful.
In an effort to implement that real-time technology, Voi is partnering with Luna, which develops computer vision algorithms aimed squarely at scooters. The collaboration uses a camera as a sensor alongside lane segmentation AI, similar to what you would see on a high-end car. Voi and Luna are explicitly targeting areas where scooters come into close proximity to humans, not only detecting pedestrians in real-time but counting them to determine how congested a place is.
If implemented smoothly, it’s possible this technology could significantly reduce e-scooter accidents. To learn more about what’s happening in the e-scooter industry, click here.