Story image

GTC18 - NVIDIA simulation will take self-driving car testing off road

28 Mar 2018

NVIDIA has introduced NVIDIA DRIVE Constellation, a cloud-based system for testing autonomous vehicles using photorealistic simulation.

The goal, they say, is to create a safer and more scalable method for bringing self-driving cars to the roads - welcome news for many considering the recent pedestrian death that shut down Uber's operation.

DRIVE Sim software can simulate different weather such as rainstorms and snowstorms, blinding glare at different times of the day, limited vision at night, and all different types of road surfaces and terrain.

Dangerous situations can be scripted in simulation to test the autonomous car's ability to react, without ever putting anyone in harm's way.

The computing platform is based on two different servers.

The first server runs NVIDIA DRIVE Sim software to simulate a self-driving vehicle's sensors, such as cameras, lidar and radar.

The second contains an NVIDIA DRIVE Pegasus Al car computer that runs the complete autonomous vehicle software stack and processes the simulated data as if it were coming from the sensors of a car driving on the road.

“Deploying production self-driving cars requires a solution for testing and validating on billions of driving miles to achieve the safety and reliability needed for customers," says NVIDIA automotive vice president and general manager Rob Csongor.

“With DRIVE Constellation, we've accomplished that by combining our expertise in visual computing and data centres. With virtual simulation, we can increase the robustness of our algorithms by testing on billions of miles of custom scenarios and rare corner cases, all in a fraction of the time and cost it would take to do so on physical roads."

The simulation server is powered by NVIDIA GPUs, each generating a stream of simulated sensor data, which feed into the DRIVE Pegasus for processing.

Driving commands from DRIVE Pegasus are fed back to the simulator, completing the digital feedback loop.

This "hardware-in-the-loop" cycle, which occurs 30 times a second, is used to validate that algorithms and software running on Pegasus are operating the simulated vehicle correctly.

"Autonomous vehicles need to be developed with a system that covers training to testing to driving," says IHS Markit research and analyst director Luca De Ambroggi.

“NVIDIA's end-to-end platform is the right approach. DRIVE Constellation for virtually testing and validating will bring us a step closer to the production of self-driving cars."

DRIVE Constellation will be available to early access partners in the third quarter of 2018.

Adobe, Microsoft and LinkedIn join forces to accelerate account-based experiences
“With these new account-based capabilities, marketing and sales teams will have increased alignment around the people and accounts they are engaging.” 
Winners of 2019 Adobe Experience Maker and Marketo Revvie Awards announced
The Adobe Experience Maker Awards recognise Adobe Experience Cloud customers and partners.
How Adobe and ServiceNow aim to advance customer experience management
“Together, ServiceNow and Adobe will help enable seamless digital workflows that power the experiences customers want.”
Adobe opens up marketing opportunities with Roku
Adobe and streaming TV platform Roku are now offering Adobe customers the ability to precisely target consumer audiences moving to over-the-top content (OTT).
Adobe Summit kicks off the future of customer experience in Las Vegas
“Today, at Adobe Summit, we unveiled significant new capabilities in Adobe Experience Cloud, including the introduction of Adobe Commerce Cloud and Marketo Engage, and general availability of Adobe Experience Platform.”
NEXTDC appointed data centre provider for Queensland Government
“NEXTDC’s appointment to the supplier panel for data centre services is an important step forward for the Queensland Government."
Ruckus releases new switch for 100GbE edge-to-core networks
Enables multi-gigabit networks with pay-as-you-grow model suitable for education, government and enterprise environments.
How AI could help cardiologists detect heart defects
Deep learning supposedly has the potential to help doctors cut down on diagnostic errors.