Nvidia Releases Drive AGX Autonomous Vehicle Dev Kit

Chipmaker Nvidia unleashed a torrent of announcements from the GTC Japan robotics convention this week, including the release of its Drive AGX Xavier Developer Kit, a platform for building autonomous driving systems.

The AGX combination of hardware and software development kit includes an AGX Xavier car computer, along with a vehicle harness to connect the platform to the car, international power supply, camera sensor and other accessories.

The open platform runs the company’s Drive Software 1.0 release, which incorporates operations including data collection, obstacle and path perception, advanced driver monitoring and in-vehicle visualization.

The software, which can be updated over-the-air, includes LaneNet and OpenRoadNet, enabling the vehicle to identify lane markings, and a driver-facing camera application that monitors the driver’s facial expression to determine if they’re drowsy or focused on the road.

Nvidia is partnering with Japanese commercial truck maker Isuzu to develop self-driving technology for using the Drive platform. Isuzu, which makes more than 600,000 commercial vehicles annually, has already begun data collection and supervised testing using Drive technology.

Within a mere three years, the worldwide market for self-driving trucks could run into more than $1 billion, an April Allied Market Research report found.

Volvo unveiled its vision for the future of commercial trucking this week as well with a self-driving tow vehicle bearing little resemblance to your classic big rig.

The vehicles boast a fully electric propulsion system with zero exhaust emissions and low noise levels, and are all linked to a cloud service and a transport control center.

The company also opened its autonomous vehicle simulation platform, Drive Constellation, to allow simulation partners to integrate complex datasets for testing and validation in the virtual world.

Constellation consists of two servers: One runs Nvidia Drive Sim software to generate the kinds of data that a self-driving car’s sensors would collect, and the other incorporates an Nvidia Drive Pegasus hardware-software platform like those designed to go into vehicles.

Pegasus is the company’s top-of-the-line in-car platform for handling so-called Level 5, fully driverless operation. It includes two of Nvidia’s new Xavier automotive chips, GPUs and AI software.

The artificial intelligence systems Nvidia develops for driving learn by experience how to detect and respond to situations, much like humans do.

Constellation draws upon Nvidia’s expertise in generating photorealistic objects and environments. In addition, the company’s GPUs have powered in-car infotainment systems for years and are poised to play a big role in future connected and autonomous cars.

Japanese auto giant Toyota, which first announced its collaboration with Nvidia in 2017, is well underway in incorporating the Drive AGX Xavier as the AI brain in its production cars beginning in 2020, and the AGX platform also integrates key sensor manufacturers like Sony, Panasonic and Omron.

Nvidia is also the founding member of the Networking for Autonomous Vehicles (NAV) Alliance, initiated in June — German auto giant Volkswagen, automotive components supplier Continental, Ethernet technology specialist Aquantia and engineering and electronics giant Bosch are among the co-founders.

— Nathan Eddy is a filmmaker and freelance journalist based in Berlin. Follow him on Twitter.

Leave a comment

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