Torc Robotics Select Amazon Web Services (AWS) to Manage the Data From its Fleet of Self-driving Trucks

author: FutureCar Staff    

A self-driving truck developed by Torc Robotics.

Autonomous vehicles generate an enormous amount of raw data that often needs to be processed in real-time while the vehicle is traveling down the road. A typical self-driving vehicle can generate terabytes and even petabytes of data each hour of operation. For this reason, autonomous and connected vehicles in the future will need to be supported by a robust infrastructure to send data to and from the cloud with little latency and the highest level of reliability.

One provider is Amazon, via its Amazon Web Services (AWS) platform, which serves as the backbone of the internet for many of the top companies in the U.S., including Netflix, Facebook and Twitter. AWS is also being utilized to process the large amounts of data for connected and autonomous vehicles.

On Wednesday, autonomous truck developer Torc Robotics announced AWS as its preferred cloud provider to handle the scale and speed needed for data transfer, storage, and compute capacity as the company prepares to deploy its fleet of self-driving test trucks, beginning in New Mexico and Virginia.

Torc said its development team will utilize AWS for both low- and high-demand tasks, as well as data sharing across remote teams. 

"AWS is an ideal platform for the ingest, storage, and post-processing of massive amounts of data collected by our on-road test fleet," said Ben Hastings, Torc's CTO.

Torc's test fleet in New Mexico is already generating petabytes of data (1 petabyte = 1 million gigabytes) from tests on public roads, the company said.

The Torc Robotics test fleet is also growing, so is the number of routes, and sensor capability, is resulting in an increase in data processing requirements from Torc's by engineering teams, which are located in both the U.S. and in Germany. 

"Our next generation fleet of test trucks will help us rapidly grow our capabilities and accelerate the commercialization of Level 4 self-driving trucks," said Michael Fleming, Torc's CEO. "Our ability to handle the data involved must be able to keep up – whether it's for transfer, storage, or scaling our simulation capability. With AWS, we have a trusted solution that provides the computing scale, transfer speed, and security when we need it."

The expansion of on-road testing routes to New Mexico follows a year of working closely with Daimler Trucks on developing a foundational structure for the commercialization of self-driving trucks, which will make freight delivery much more efficient and safer.

Torc is an independent subsidiary of Daimler Truck AG, which is tasked with commercializing a SAE Level 4 autonomous system that will be offered to freight customers, which requires no human intervention in most operating environments. 

Daimler acquired a majority stake in Torc Robotics in 2019 for an undisclosed sum.

"We believe this relationship between Torc and AWS brings together two very strong teams and is another milestone on our road to Level 4 trucks," said Dr. Peter Vaughan Schmidt, Head of Daimler Trucks' Autonomous Technology Group.

Torc Robotics was founded in 2005 by a group of Virginia Tech students who built three autonomous cars to compete in the annual AUVSI Intelligent Ground Vehicle Competition (IGVC), which is an annual international robotics competition for college students. Teams that compete in the annual IGVC design and build an autonomous ground vehicle capable of completing difficult challenges.  

The three Virginia Tech students placed first, second, and third in the competition, which led them to found the company. Torc Robotics is headquartered in Blacksburg, Virginia.

Over the years, Torc has integrated its self-driving technology on a wide variety of vehicles from passenger vehicles to 300-ton mining trucks. Working with the U.S. Department of Defense, Torc outfitted vehicles with technology capable of detecting and removing roadside IEDs (improvised explosive devices),

Since launching in 2006, AWS has grown into one of the world's biggest cloud-infrastructure providers. In the first quarter of last year, AWS brought in a record $10 billion of revenue, accounting for nearly 14% of Amazon's total revenue for the quarter. 

The e-commerce company now controls more than a third of the cloud computing market, almost twice its next closest competitor Microsoft with its Azure platform. 

AWS provides rapid and secure data transfer, intelligent storage, analytics tools, and high-performance multi-core CPU and GPU computing resources to help Torc rapidly scale its platform and accelerate its testing and commercialization of autonomous driving technology. 

Torc's autonomous driving software collects and processes raw data from multiple sensors such as lidar, radar and cameras, which must be fused and processed. Torc's next-generation of trucks will be even more advanced, using more sensors at higher resolutions for the trucks' long-range perception systems, which further increases the magnitude of data for analysis and machine learning.

"The race to develop self-driving vehicles generates massive volumes of data from many types of sensors. With AWS, Torc engineers have the speed, flexibility, and insights they need to design tests, run simulations at scale, and refine their experiments using a broad range of highly specialized compute instance types," said Wendy Bauer, Director of Automotive Sales, AWS. "By pairing Torc's industry-leading technology with AWS's reliability, security, and deep expertise in autonomous vehicle development, Torc is positioned to remain a leader and introduce the benefits of self-driving trucks to society."

Torc will also leverage AWS managed services such as Amazon Elastic Kubernetes Service (Amazon EKS) for running simulation software at scale and Amazon Simple Storage Service (Amazon S3) Intelligent-Tiering to efficiently manage test data and support regulatory compliance. 

This integration on AWS will allow Torc to transfer massive amounts of data for the analysis of real-world tests, while also providing computational power for simulation and deep learning.

"Our software is tested in simulation using a combination of synthetic scenarios and replayed sensor data," said Hastings. "These tests often stack up in ways that create significant peak demands for compute resources. With AWS, we get a solution that can dynamically scale to meet the needs of the engineering and virtual testing teams without having to acquire and maintain our own data centers."

Daimler Trucks is one of the first companies to develop autonomous trucks. In 2014, the division demonstrated its "Mercedes-Benz Future Truck 2025", the world's first automated truck at the time. The demo took place on a closed-off section of the Autobahn near Magdeburg, Germany.

In 2019, Torc added Freightliner self-driving trucks to its fleet. Daimler Trucks has owned U.S. truck maker Freightliner since 1981. 

FutureCar Staff