tokyo
tokyo

Tokyo freeway copied for driverless cars

Riley Riley

Engineers have created a virtual copy of Tokyo’s notorious Inner Circle Route that is accurate to 1mm to use in the development of driverless vehicles.

Simulation software specialist rFpro has created the copy of Tokyo’s Shuto Expressway, Inner Circular route, signposted as route C1, specifically for vehicle engineering developers.

The complex section of road includes some 22 interchanges and is the setting for many racing games, not to mention real-life escapades.

Simulating some of the world’s most challenging roads in this way significantly accelerates the training of artificial intelligence (AI) by reducing cost and risks of collecting real world data, says rFpro.

The Inner Circular Route, signed as Route C1, is one of the routes of the Shuto Expressway system serving the central part of the Greater Tokyo Area.

The route is a complete loop around the central Tokyo wards of Chiyoda, Chūō, and Minato, with a total length of 14.8km.

In addition to serving areas of central Tokyo, the Inner Circular Route also serves as the origin of the radial routes of the Shuto Expressway.

A section of the expressway is built above the Shibuya River.

The virtual environment has already been adopted by major vehicle manufacturers predominately for the development of autonomous vehicles.

The complete 35km section of road has been modelled using survey-grade LiDAR scan data to create a vehicle dynamics grade road surface, which is accurate to within 1mm.

This is key to accurately simulate the effects of every bump, drain cover and expansion joint around the full route.

The environment is not only geometrically precise but functionally accurate too with each of the thousands of road signs, markings, and roadside objects being individually classified.

This is critical for the development of many ADAS and autonomous systems that rely on panoptic segmentation for their training data sets.

“The C1 route is one of the most challenging stretches of city roads in the world for an autonomous vehicle to navigate,” rFpro Managing Director, Matt Daley, said.

“With constantly changing road curvature and elevation, complex and densely situated junctions and a huge array of road signs and markings, it is the ultimate test of autonomous vehicle technologies and is the perfect way to exercise and develop such capabilities safely.”

[irp]

The digital twin also enables users to add in intelligent and scripted traffic to create an almost infinite number of test scenarios in this model.

The types of vehicles, their speeds, colour and density of traffic can be varied and more.

The rFpro system also allows a large number of humans to drive in the model at the same time, enabling the most complex edge case scenarios to be created and recorded.

This offers a cost and time-effective way of creating large quantities of usable training data to improve a vehicle’s artificial intelligence.

“Collecting the volume and variety of training data needed for this type of road network would be very expensive, time consuming and potentially dangerous in the real world,” Daley said.

“Our model of Tokyo’s C1 brings this highly complex road network to development engineers and researchers, wherever they are in the world.”

The Tokyo Expressway is the latest in an ever-growing library of highly accurate digital twins created by rFpro that consists of more than 100 locations of other public road routes, proving grounds and test tracks.

“There are a large number of private models too that have been commissioned by our customers of their own proving grounds and testing locations.” he added.

Due to the high fidelity of the models, rFpro’s digital twins are also effective in the engineering and development of other areas of a vehicle, including vehicle dynamics handling, braking and steering work.

“Our models are extremely versatile, enabling users to maximise their investment in simulation.

“You can even replicate complex traffic scenarios to test how well your automatic gearbox and engine mapping perform when crawling through traffic.

“Importantly, this can then be correlated in the real world on the exact same piece of road,” Daley said.

CHECKOUT: Driverless cars learn how to drive like us

CHECKOUT: Driverless crash: who’s to blame?

Your email address will not be published. Required fields are marked *


Riley