Torc partners with Flex, NVIDIA on AI platform for AVs

Torc Robotics is collaborating with Flex and NVIDIA to create a scalable physical AI computing system for autonomous trucks. For this system, Torc collaborated with NVIDIA on a multi-chip adaptable architecture using DRIVE AGX, the DRIVE Orin system-on-a-chip, DriveOS’ operating system, and Flex’s Jupiter compute design platform and manufacturing.

“NVIDIA DRIVE AGX has been industry-proven in full production for automotive real-time applications at the edge,” said Rishi Dhall, Vice President of Automotive at NVIDIA. “It delivers the high compute performance, low latency, and multi-sensor connectivity needed for Torc’s sophisticated autonomous trucking software, delivering robust perception, prediction, and planning for safe and reliable operation.”

The AI system will grant Torc a scalable, high-performance production hardware and software platform based on the Freightliner Cascadia, the companies said, which is designed to be able to support autonomous driving capabilities. Torc said that it validated its driverless operations, using this AI technology, at highway speeds in 2024.

The companies said that the NVIDIA DRIVE solutions and Flex’s automotive compute design all adhere to Torc’s size, performance, cost, and reliability requirements for fleet customers, providing a “true Software Defined Vehicle functionality” that will be able to adapt to new lanes, new routes, new hubs, new hardware and sensor configurations, new operational rules, and new road conditions.

"With Daimler Truck’s autonomous-ready Freightliner Cascadias  with in-built redundancy, our work with NVIDIA and Flex is already providing a stable and proven foundation for Torc's autonomous vehicle technology," said Torc’s CEO, Peter Vaughan Schmidt.