Startups test safety systems in Michigan

As many as five more companies could receive grants this week, and two more testing locations could be added. In June, Phillips said, a delegation from Michigan will attend EcoMotion, a conference that showcases Israeli tech startups in Tel Aviv, and seek to attract more companies.

Here's a closer look at the testing these startups have begun in Michigan.

Derq's artificial intelligence is designed to do two things. It makes accurate inferences about vehicles that are going to run red lights before they do it, and it broadcasts immediate warnings to vehicles in the area. It also predicts the intentions of pedestrians and other vulnerable road users and alerts vehicles if a conflict is anticipated.

The system must make such forecasts with enough time to give motorists a two-second warning.

HAAS Alert
Six years ago, HAAS Alert founder Cory Hohs was nearly struck by an ambulance speeding through an intersection in Chicago. The experience stuck with him. In his mind, a flashing light isn't sufficient warning.

So he created an aftermarket transponder about the size of a deck of cards that fleet managers of emergency vehicles can install themselves. The devices can understand real-time location, and further understand if the lights on the vehicles are flashing or whether buckets are deployed on utility vehicles.

All that information can be disseminated via cellular networks. Alerts are available through the company's app or integrated on the Waze navigation app.

The Grand Rapids Fire Department has installed HAAS Alert on vehicles throughout the western Michigan city. As the pilot project has gained traction, Hohs says he has heard from an unexpected contingent — ride-hailing drivers who are deaf or have partial hearing loss are interested in receiving visual alerts.

The information becomes no less important in an autonomous era.

"In automated vehicles, this becomes even more critical," Hohs said. "We're coming from an off-board sensor using cellular technology to tell a vehicle what's coming up and who's about to blow the light at an intersection."

Humanising Autonomy
One key challenge for autonomous vehicles is that it's not enough to detect and identify obstacles in their paths. They need to understand how those obstacles, namely vulnerable road users, are going to behave in the immediate future to seamlessly function.

"For now, autonomous vehicles are being trained in low-density pedestrian environments like Phoenix or Mountain View [Calif.], and there's a reason it's being done there," says Leslie Nooteboom, a co-founder of Humanising Autonomy, headquartered in London. "It's easier to drive where there's less people. If you want these vehicles to truly drive in cities or crowded urban environments, they'll need to understand people."

To do that, the company uses AI to evaluate behavioral patterns and movements to anticipate with a high degree of accuracy whether people plan to cross a street or wait for passing traffic.

Already working with Daimler and European aerospace company Airbus, Humanising Autonomy is testing a permutation of its technology in Ann Arbor that isn't intended for self-driving vehicles, but instead for city buses. The company is collaborating with the Ann Arbor Area Transportation Authority to give bus drivers alerts on the likely actions of vulnerable road users.

"The metric we're seeing and shooting for is an ability to predict true positives 90-plus percent of the time, and we're doing that with extremely low false positives," said Will Foss, director of business development and partnerships for Derq, which received an $80,000 grant from PlanetM.

Foss said the company plans to expand testing in Michigan and elsewhere in the U.S. next year. Though the company remains agnostic on whether its V2X, or vehicle-to-everything, warnings are sent via Digital Short Range Communications or over cellular networks, Derq has demonstrated its software while using Qualcomm's cellular chipsets, which can alert autos that have V2X built in or have an aftermarket receiver.

An unforeseen benefit has developed since Derq started testing. As the use of e-scooters has sprouted around the city, the company's data has given city transportation officials and safety advocates insight into where and how they move around.

"Before, it was bikes and pedestrians," Foss said. "Now there's a whole new class of vulnerable road users that are kind of on the sidewalk, sometimes not, and kind of like a bike, but not a bike. So we're looking at their usage and behavior, and learning to predict and understand how they're impacting risk."

Article courtesy of autonews.com