Torc Robotics has selected Amazon Web Services (AWS) as its preferred cloud provider to handle the scale and speed needed for data transfer, storage, and compute capacity as the company begins testing its fleet of autonomous trucks in New Mexico and Virginia. Torc Robotics, an independent subsidiary of Daimler Trucks, is responsible for commercializing a SAE Level 4 autonomous system that will be offered to trucking customers.
With a growth in the test fleet size, number of routes, and sensor capability, Torc identified an increase in data ingestion and analysis needs that required the cloud computing capabilities of AWS; its fleet in New Mexico is already generating petabytes (one petabyte = one million gigabytes) of data from tests on public roads.
One source of this data is Torc’s end-to-end software stack that collects and processes raw data from multiple sensors – such as LiDAR, radar, and cameras. The company’s autonomous vehicle system utilizes on-board computers that process sensor data in real time and host software that handles dynamic driving tasks during autonomous runs.
In addition to the increased number of routes, and the expanded fleet size, Torc indicated that the next generation of their test trucks will adopt more sensors at higher resolutions. Together, these sensors will work to enhance object detection at longer ranges – further increasing the magnitude of data to be used for analysis, simulation, and machine learning. Torc will utilize AWS to increase the efficiency of data transfer from its on-road routes as their team continues to enhance the system. Its development team will leverage AWS for low and high-demand tasks, as well as data sharing across remote teams.
Torc will also leverage a variety of AWS-managed services – including Amazon Elastic Kubernetes Service (for running simulation software at scale), Amazon Managed Streaming (for Apache Kafka), Amazon Managed Workflows (for Apache Airflow), and Amazon Simple Storage Service Intelligent-Tiering (to manage test data and support regulatory compliance). By integrating with AWS, Torc will be able to transfer massive amounts of data for log analysis of real-world testing and provide computational power for simulation and deep learning.