A Product Release, Not a Demo: Why Torc’s Autonomous Product Release v0.1 Was ‘The Next Step’

A Product Release, Not a Demo: Why Torc’s Autonomous Product Release v0.1 Was ‘The Next Step’

Torc has begun successful advanced validation of our autonomous trucks without a driver in a multi-lane closed-course environment.

As Torc Robotics nears its 20th year of operations in 2025, it has achieved an incredible milestone: a fully self-driving product release validation. More than just a demo, this milestone manifests the hard-won lessons behind Torc’s R&D, advanced engineering, artificial intelligence, machine learning, software best practices, and operational excellence. But if you look past the dramatic images of no human behind the wheel of an 18-wheeler moving at 65mph, it represents a powerful step forward toward an efficient and sustainable freight system that will reshape our supply chain… and you also have a rather standard production stage step.

The autonomous drive without a human driver was a straightforward, product milestone. Additionally important, it marked the critical next step from Torc’s advanced engineering phase to productization on a unified, embedded platform. Not a bolt-on solution, Torc’s integrated Freightliner Cascadia is autonomous-ready, creating more efficient, profitable way to move freight across middle mile routes.

The productization stage of any development process is meant to prove that a product was built correctly, in both reference to customer pain points and needs, and in our case, using automotive and software best practices to create a road-worthy product. Every software you’ve ever used or product you’ve ever bought has likely had some form of product validation stage. In our self-driving truck validation, we need to address the fact that the community needs a safe vehicle for the long-haul journeys wherein a human driver is unavailable. Therefore, our truck must be able to drive on its own. So, our product validation was more than just a demo – it was real time, real speed proof that the software can do what it’s supposed to do, as well as a demonstration of what this technology can do for our customers and our communities.

Amazon originally started as just an online bookstore in the mid-1990s. Jeff Bezos wanted to create “an everything store” but knew that the first step to a full-scale productization needed a controlled, narrow focus. He chose books because they were easily sourced and shippable from specific warehouses, and introduced a simple online storefront. Through this product validation, Amazon was then able to work on logistics, customer service, and online services.

The Torc product management team is quick to point out that this milestone wasn’t a demonstration but simply a stage in a product release lifecycle, marking the next stage of product maturity. “All software needs to have this step to be created,” says Sheila Scanlon, Vice President of Product Management. “You don’t release software until it’s passed all the tests, and while this test was amazing to see, it was a product validation event. This release ties completely back to our product roadmap with a subset of the end features being fully tested and verified, but no software release is ever the ‘final’ release. It’s just like your cell phone: It’s constantly getting upgrades, as will our software.”

Larry Page and Sergey Brin, two PhD students, had the software know-how to create a better and faster search algorithm. They tested on a small controlled, gated data pool at first, Stanford University’s computer network, as their first product validation. After positive feedback and expansion, that search algorithm eventually became Google.

The company’s applied and responsible artificial intelligence (AI) applications, system architecture, production-intent embedded hardware, and directing safety engineering all joined up to get the truck on the road autonomously. From this point until market entry, Torc is working on fully vetted, tested, and traceable software. Our product validation stage is just one chapter in a much longer story.

“This product is never going to be done. This was one step. We’re continuing to build upon the product capabilities and features, with every additional release until our version 1.0 release, which will be available early 2027,” says Scanlon. “It’s a subset of the feature complete. It’s always going to be growing and expanding. New sensors and hardware will be created, and we’ll have better and better capabilities and more and more features, which will allow us to expand our ODD or expand the roads.”

At Torc, we’re targeting initial use cases across the southern United States for our first commercial product launch, scheduled for 2027. Our product validation event has proven that our first leg of freight, in Texas, is a feasible and achievable use case for our technology. As we develop new features and unlock new routes, our self-driving semis will become a powerhouse of safe, efficient, and easy freight.

 

Driving the Future: Spotlighting the Torc Machine Learning Frameworks Team

Driving the Future: Spotlighting the Torc Machine Learning Frameworks Team

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.”

“As part of the Frameworks team, my daily work focuses on building a robust and scalable deployment infrastructure to ensure that every machine learning model operates with the highest reliability in an L4 autonomous environment. By driving seamless integration of complex ML models on embedded hardware, optimized for real-time performance, we are setting new industry standards. This infrastructure is critical for autonomous trucks to navigate dynamic road conditions safely and efficiently, and it reflects the foundational work I do each day to advance Torc’s leadership in autonomous freight.”

Yashovardhan Chaturvedi

Machine Learning Engineer, Torc

 

Long-Term Impact

The impact of the Torc ML Frameworks team is forward thinking. As autonomous vehicles become more prevalent, the robust, scalable systems developed by this team will be essential for:

  1. Rapid adaptation to new road conditions and scenarios
  2. Seamless integration of advancements in AI and machine learning
  3. Scaling our compute needs with a strong, cloud-based backend
  4. Monitoring and securing data standards

“In essence, we’re building the brain that will power the Torc autonomous trucking software,” Jourdan explains. “Our work today will enable more efficient logistics, and a robust transportation industry “

Spotlight on Innovation

Torc’s strength is its people. The ML Frameworks team is driven by the collective efforts of talented individuals working together to push the boundaries of what’s possible. The Joint Training Framework and Joint Deployment Framework is the groundwork for an adaptable future for autonomous technology.

Key contributors like Achyut Boggaram have been instrumental in designing and implementing crucial components such as Unified Data Loading Pipelines and Joint Deployment Framework. This technology enhances our ability to process complex sensor data and streamline our model deployment process, significantly reducing the time from development to real-world testing.

The team’s contributions extend beyond technical development. They’ve built a collaborative community spanning multiple divisions within Torc, fostering knowledge sharing and driving innovation. Their mentorship and proactive approach to problem-solving have been invaluable.

Botschen emphasizes, “The dedication and innovation shown by our ML Frameworks team is what makes our ambitious goals achievable. Their ability to solve complex problems, collaborate across teams, and continuously push the boundaries of what’s possible is what sets Torc apart in this competitive field.”

At Torc, we’re proud of the groundbreaking work our ML Frameworks team is doing. As we continue to drive the future of freight, we’re driven by a vision of safe, more efficient transport, Stay tuned for more updates as we continue our journey toward bringing L4 autonomous trucks to market.