Damon’s AI Hypersport Improves Motorcycle Safety

For all its purely electric acceleration and autonomy and its ability to metamorphose, the Hypersport motorcycle Attach last week at CES by Vancouver, Canada Damon motorcycles matters for only one thing: it is the first motorcycle wrapped in active safety systems.

These systems do not take control, even in anticipation of an accident, as they do in many advanced driver assistance systems in cars. They leave a rider in control while providing the benefit of an extra pair of eyes.

Why drape high tech “rubber padding” over the motorcycle world? Because that’s where the danger lies: motorcyclists are 27 times more likely to die in an accident that car passengers.

“It’s not about if you will have a motorcycle accident, but whenSays Damon CEO Jay Giraud. “Nobody gets on the bike knowing that, but they are learning. “

Image: Damon Motos

The Hypersport’s sensor suite includes cameras, radar, GPS, solid-state gyroscopes, and accelerometers. It doesn’t include lidar – “it’s not there yet,” says Giraud – but it opens the door to another way of seeing the world: wireless connectivity.

The brain of the bike logs everything that happens when danger looms, including warnings issued and evasive maneuvers taken, then directs the data to the cloud via 4G wireless. For now, this data is being processed in batches, to help Damon refine his algorithms, a common practice among self-driving car researchers. Someday, it will share that data with other vehicles in real time, a strategy known as Vehicle to Everything, or V2x.

But not today. “This whole world is in 5 to 10 years, at least”, complains Giraud. “I’ve been working there for over ten years – we’re no closer today than in 2008.”

System diagram

Image: Damon Motos

The bike has an on-board neural network whose parameters are fixed at all times. When the cloud network offers improvements, these are sent as live updates to each motorcycle. Updates must be approved by each owner before being uploaded on board.

When the AI ​​detects a danger, it gives a warning. If the car in front suddenly brakes, the handlebars shake, signaling a head-on collision. If a vehicle coming from behind enters the rider’s blind spot, the LEDs will flash. This eliminates the need for the pilot to constantly look back to check the blind spot.

Above all, it gives the rider time. A National Highway Traffic Safety Administration Report 2018 found that 75 to 90 percent of riders involved in crashes had less than three seconds to notice a threat and try to avoid it; 10 percent had less than a second. One or two more seconds could save many lives.

The models that the motorcycle AI extracts from the data are not always comparable to the ones that a self-driving car would care about. A motorbike goes from one half of the lane to the other; he leans over, sometimes approaching the sidewalk terribly; and it is often difficult for drivers of other vehicles to see.

A motorcycle-centric problem is the high risk a rider takes just by entering an intersection. About three-quarters of motorcycle accidents happen there, and of that number about two-thirds are caused by a car crash from behind or from the side. The side impact, called a T-bone, is particularly bad because there is nothing at all to protect the pilot.

Certain traffic patterns increase the risk of such collisions. “The repeating models allow our system to predict risk,” explains Giraud. “As the cloud sees the tagged information over and over again, we can use it to make predictions. “

Damon is accepting pre-orders, but he plans to start shipping in mid-2021. Like You’re here, it will deliver directly to the customer, without any reseller obstructing the passage.

Editor’s Note: Updated Jan 29, 2019 to remove the word “chopper” to describe this bike.

Source link

About the author