AI Business is part of the Informa Tech Division of Informa PLC

This site is operated by a business or businesses owned by Informa PLC and all copyright resides with them. Informa PLC's registered office is 5 Howick Place, London SW1P 1WG. Registered in England and Wales. Number 3099067.

Transport

Tokyo Expressway simulator to speed up car AI development

by Graham Hope
Article Image

If it can navigate the Shuto Expressway, it can drive anywhere

A digital replica of one of the world’s most famous road systems has been created to help the development of autonomous cars.

Simulation expert rFpro has produced a copy of Tokyo’s notorious Shuto Expressway, renowned the world over for its bewildering mix of traffic, elevations, bends, junctions, confusing road signs and markings.

Testing self-driving vehicles in such an environment is exceptionally difficult, so Hertfordshire-based rFpro believes it has come up with a solution in the form of simulation.

The replica, which will be used by the world’s leading car manufacturers, will speed up the training of AI-based systems by reducing the costs involved in collecting real-world data, as well as eliminating the risks.

Virtual Tokyo

The road – also known as the C1 route Expressway –has been modeled using LiDAR scan data. This has allowed rFpro to create a ‘vehicle dynamics’ grade road surface, which is accurate to within 1mm. That means the simulator can replicate the effects of every road imperfection, drain cover and expansion joint on the 35km route.

In addition, every one of the thousands of signs, markings and roadside objects on the Expressway are represented too – a necessity for the successful development of advanced driver assistance and autonomous systems.

It is also possible to model traffic, and vary its density and the type of vehicles involved, to produce an almost infinite number of test scenarios.

By enabling a large number of people to drive in the simulation at the same time, ever more complex testing can be carried out, improving vehicles’ artificial intelligence in a cost-effective, time-efficient and safe manner.

“The C1 route is one of the most challenging stretches of city roads in the world for an autonomous vehicle to navigate,”Matt Daley, managing director at rFpro, said. “It is the ultimate test of autonomous vehicle technologies and is the perfect way to exercise and develop such capabilities safely.

“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 simulator is the latest addition to rFpro’s growing library of more than 100 public roads, test tracks, and proving grounds. The company has also found success delivering virtual versions of individual customers’ proving grounds. The simulations are used to test all aspects of a vehicle, including handling, steering and braking. “Our models are extremely versatile, enabling users to maximize their investment in simulation,” Daley said.

Practitioner Portal - for AI practitioners

Story

MLOps startup Verta gets $10m in funding, launches first product

9/1/2020

The company plans to commercialize open source ModelDB project, developed by CEO Manasi Vartak

Story

AI and analytics services: Capabilities and costs

8/27/2020

Which skills do you need in your team? What are the costs for running the service? How can you optimize them? These are three key questions when setting-up and running an AI and analytics service.

Practitioner Portal

EBooks

More EBooks

Upcoming Webinars

Archived Webinars

More Webinars
AI Knowledge Hub

AI for Everything Series

David Hardoon explaining recent developments in Data Science and AI

Author of Getting Started with Business Analytics: Insightful Decision-Making and the forthcoming book, Creating a Data Culture: Failing to Succeed

AI Knowledge Hub

Experts in AI

Partner Perspectives

content from our sponsors

Research Reports

More Research Reports

Infographics

Smart Building AI

Infographics archive

Newsletter Sign Up


Sign Up