Parallel Domain has unveiled a virtual world-generation technology that will allow the conduction of large-scale training and testing of autonomous cars before they start operating on public roads.

The company also revealed that it raised $2.5m through a seed funding round, which was led by Costanoa Ventures and Ubiquity Ventures.

Autonomous vehicles and ground transportation market is expected to grow significantly in the future.

To achieve an acceptable level of safety, these self-driving vehicles need to drive an estimated 11 billion miles to exceed current human standards and be capable of performing under critical cases.

Parallel Domain founder and CEO Kevin McNamara said: “Driverless cars need massive quantities of challenging training miles in order to learn how to drive safely, but these real-world miles are dangerous, expensive, and inflexible.

“State-of-the-art simulations alleviate these bottlenecks while providing essential interactivity, control, and reproducibility.”

“State-of-the-art simulations alleviate these bottlenecks while providing essential interactivity, control, and reproducibility.

“Our software automatically generates the environments and scenarios that feed into simulators, making it safe and fast for autonomous vehicles to learn from their mistakes, accelerating time to safety for all vehicles.”

Parallel Domain platform is said to be faster than the other simulators and it can develop multiple realistic, highly detailed virtual city blocks in less than a minute.

Accordingly, it provides the foundation to carry out simulated training and testing environments for autonomous vehicles.

The platform allows the usage of real-world map data to create the virtual world with traffic, pedestrians and time of day.

Furthermore, it also allows users to adjust other elements and customise according to the requirement, including the number of lanes, road curvatures and other features with a few mouse clicks.