Humans see, perceive, and process their driving environment through two eyes, 180 degree peripheral vision, two ears, and three mirrors.
Motional’s driverless vehicles process that same environment through a sensor suite of advanced LiDAR, cameras, and radar that see up to 300 meters away, and a full 360 degrees around the vehicle. This superhuman vision enables driverless cars to respond faster and more safely than a human ever could. And they’re already doing so in cities around the world.
But what if we could even further enhance our technology’s already superhuman vision? Would it make it easier to navigate challenging scenarios, such as multi-lane intersections? Could it enable vehicles to respond in ways that create a smoother and more comfortable ride?
The Motional + Derq Pilot: A Bird’s-Eye View
We’ve partnered with Derq, an AI company developing innovative road solutions, to find those answers. Together, Derq and Motional are testing how driverless technology reacts when given an even broader perspective than it already has: a bird’s-eye view.
Derq is at the forefront of using AI and vehicle-to-everything (V2X) technology to create safer roads. In the pilot, cameras, placed high up in busy intersections and connected to Derq’s AI systems running on roadside computers, will transmit data to Motional’s vehicles. This data will provide Motional with a different view of some of the toughest intersections they’re navigating. From their elevated vantage point, Derq’s system can see cars exiting parking lots, pedestrians stepping between parked cars, and cyclists weaving through cars stopped at a red light. It can also predict their movements to provide advance notice of potentially challenging interactions with Motional’s vehicles. And this data is available even before a Motional vehicle enters the intersection. Watch this video to see how it works.
Initially, Motional and Derq will evaluate the different viewpoints (from Motional’s sensor suite and Derq’s cameras) offline. By studying the data offline, we can replay a scene over and over, and examine how the driverless vehicle navigates the scene with and without the extra data from Derq’s cameras.
Later in the pilot, Motional’s vehicles will receive Derq’s bird’s-eye view data in real time to help inform their driving. The vehicles will process that view alongside the data received through the vehicles’ LiDAR, cameras, and radar, to make the safest and smartest driving decisions.
We anticipate that along with helping the vehicles navigate challenging scenarios, the extra viewpoint will also enable them to make smoother decisions, leading to a more enjoyable ride for the passenger. For example, braking more gradually for a traffic obstacle or shifting lanes earlier for an upcoming turn.
In addition to providing real-time bird’s-eye view data to Motional’s vehicles, Derq’s technology can also detect and alert road operators about dangerous traffic incidents unrelated to autonomous vehicles, such as crashes and wrong-way drivers. Derq can in turn build a better understanding of safety hotspots on roads and feed this information back to the AVs and road operators for better routing, design, and planning.
The Implementation
Motional and Derq are launching the pilot at two high traffic intersections in Las Vegas. The intersections were selected for their complexity, which includes:
- Significant pedestrian and cyclist interactions (pedestrian crossings and bike lanes)
- Challenging sight lines due to trees, signs, and other large obstacles
- Complex vehicle interactions among multiple lanes of traffic
These intersections also have existing smart infrastructure that was installed to help Motional and the local governments monitor and manage these challenging roadways. The pilot will launch this spring. We look forward to sharing our findings from the program down the road.
Motional has a long history in Las Vegas, including operation of the world’s longest-standing public robotaxi fleet, and is proud to work with local officials on this industry-leading research.
“The City of Las Vegas strives to build a world-class city through planning, developing, and implementing innovative solutions for our unique challenges. The operation of the Motional driverless vehicles in the Las Vegas area has provided our residents another mode of transportation among the other many multi-modal options available. We look forward to continued innovation as we build a sustainable and resilient community.” - City of Las Vegas Department of Public Works Transportation Engineering Division
Building safer roads
Motional and Derq share a common goal to create safer streets through technology innovation. Through this partnership, we’re finding new ways to make driverless vehicles even more advanced, which will lead to wider, faster, and more effective deployments.
A world full of driverless vehicles means a world with fewer accidents caused by human error, and millions of lives saved. That’s why we’ll never stop innovating.
