Torc’s autonomous software system is constructed in part from machine learning and artificial intelligence components. The Torc Machine Learning Frameworks team is creating the software stack which learns from the data collected by our fleet of trucks in on-the-road testing. This group of engineers is responsible for the automated training of machine learning models, and then the automated testing and deployment to our embedded hardware.
“Our goal is to enable rapid iterations of our autonomous software ML stack and optimize our training and deployment processes,” says Nicolas Jourdan, Engineering Manager of the ML Frameworks team. “This work is crucial for accelerating the development of safe, reliable autonomous trucking technology.”
Breaking New Ground
The team’s efforts center around two ML initiatives: the Joint Training Framework (JTF) and the Joint Deployment Framework (JDF). The JTF restructures how ML models are trained, while the JDF transforms how these models are eventually deployed to our autonomous ready Freightliner Cascadia trucks.
Recently, the team reached a significant milestone: automated model optimization and deployment tests on Hardware-in-the-Loop (HIL) benches. Instead of having to request a truck for every deployment test of machine learning components, the teams can run tests on mirroring embedded hardware, which is tightly integrated in the cloud workflows of the team.
This breakthrough allows Torc to test ML models in a production-like environment more efficiently and scalable than ever before.
The Key to L4 Autonomy
The ML Frameworks team’s work is crucial for making Level 4 autonomous trucking a reality on U.S. public roads. “Our frameworks and standards are the backbone that will enable rapid product software releases,” Jourdan emphasizes. “In the fast-paced world of autonomous vehicle development, this ability to iterate quickly and deploy safely is what will set Torc apart.”
A Vision of Transformative Change
Fiete Botschen, Torc’s division lead for the Machine Learning Training and Release Factory, highlights the transformative potential of Machine Learning: “At Torc, we are not just developing autonomous vehicles. We are developing a data driven ecosystem, which allows us to improve our trucking software stack purely by consuming the data our trucks are collecting. This is the key enabler for expanding our logistics network. We will be able to scale our business rapidly once our production trucks hit the road.”
