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.

Embracing the Future: Torc Robotics’ Emerging Talent Program

Embracing the Future: Torc Robotics’ Emerging Talent Program

 

As part of our efforts to attract the best talent in autonomous technology, we’re constantly evolving our recruitment efforts. From creating strategic partnerships with educational institutions to expanding our co-ops, internships, and early career full time opportunities, we’re committed to finding and nurturing the best minds in the autonomous trucking industry.

In order to achieve our world-class recruiting goals, we’ve expanded our early-career tactics beyond the traditional university pathway and into our newest initiative: The Emerging Talent Program, encompassing community colleges, candidates of diverse backgrounds, and more.

About the Emerging Talent Program

This purposeful decision to expand our early career pathways aims to create a broader, more inclusive vision of our autonomous world. At Torc, we’re evolving with the global workforce to create new opportunities for future engineers, AI experts, and freight professionals.

Our new Emerging Talent program is centered around embracing diversity and nurturing the potential of individuals from all backgrounds. Whether you’re looking for early career opportunities in engineering or fleet operations, we’re encouraging our company to embrace all levels of talent, driving innovation and growth within our self-driving development teams. As we move towards this comprehensive approach, we’re building our methods on the following pillars:

  • Non-Traditional Pathways. “Emerging Talent” encompasses individuals from diverse educational backgrounds, including but not limited to community colleges, HBCUs, HSIs, MSIs, and more. coding bootcamps, vocational schools, and apprenticeships.
  • Partnerships and Engagement. This program allows us to engage with talent at the K-12 level, allowing us to showcase future career opportunities to our community.
  • Recognizing Diverse Age Groups. Not all students follow the traditional path of entering and graduating from their educational path in their early twenties; our plan encompasses those who might be shifting careers, returning to the workforce after caring for family members, or entering a brand-new field of study.
  • Focusing on Potential, Not Pedigree. We put emphasis on talent and skills over educational background. At Torc, your dedication to your work and experience is what helps carry our self-driving technology forward.
  • Development Focus. We’re focused on nurturing and developing our team’s talent through their early career stages and beyond, allowing each individual to unlock their true potential at Torc.

 

Beyond Theory, Into Execution with KIT

One of our first forays into this new initiative includes our partnership with Karlsruhe Institute of Technology (KIT). As part of our collaboration with KIT, we’ve created a robust talent pipeline that encompasses both students and full-time employees. Through this partnership, we’re able to engage with top-tier talent from KIT’s innovative global community.

Simon Schaefer – From KIT to Torc Robotics
Simon Schaefer exemplifies the success of Torc’s Emerging Talent strategy. As a former student at KIT, Simon was a member of the Formula Student team “KA-RaceIng”, where he and his team built an autonomous race car. Thanks to Daimler Truck and later Torc sponsoring and supporting this team, Simon discovered Torc as an attractive employer and successfully applied for a job. Since then, he has transitioned seamlessly into his role at Torc where he works on the Vehicle Intent team. Simon has become a model employee and ambassador for our self-driving technology, complete with the hands-on experience in engineering and teamwork that KIT fostered in him. As an ambassador, Simon continues to foster the relationship between Torc and KIT, helping to attract and mentor the next generation of engineers.

Setu Namburu – Nurturing Early Career Talent

As a Manager of Applied Data Science at Torc, Setu is a key part of developing and delivering data-driven solutions for our self-driving technology. Using her extensive skills and background, she’s successfully converted five data science/analytics internship students into full-time employees during her time at Torc, showcasing her dedication to nurturing early career talent. Her leadership has been instrumental to Torc’s shift into this new program. Through her ability to guide, mentor, and advocate for early career professionals, Setu sets an incredible standard for our recruiting future.

Christin Scheib – From Europe to Blacksburg

Originally a student at Karlsruhe Institute of Technology and a Torc co-op, Christin has successfully transitioned to a full-time engineering role, moving from Europe to Torc’s HQ in Blacksburg, Virginia in the process. Since starting her work in automated truck technology, Christin’s efforts have allowed our hardware and software components to come together seamlessly, showcasing the potential that students can offer when converted to full-time employees.

Brent Papenfuse – Transforming Student Excellence to New Heights

Brent has been a key part of revolutionizing what recruitment means at Torc. In his capacity as Program Manager, Brent not only develops certification programs and maintenance procedures for our autonomous trucking solution, but spearheads hiring initiatives from technology schools and community colleges. He has also partnered with the Emerging Talent community program to influence company roles in diesel mechanics, fostering a new generation of professionals that is both technology-forward and rooted in traditional mechanics.

Alexia Tran – Propelling Achievement Across Borders

Alexia started her Torc journey as a research and development intern at Torc’s Montreal offices, where she developed state-of-the-art test benches, reverse engineered CAN bus messages, and more. After demonstrating her outstanding skills in everything autonomous engineering, Alexia was hired on as a full-time Systems Engineer. Alexia is a proud example of Torc’s community of globe-trotting professionals, having moved from Montreal to Torc’s Stuttgart, Germany offices in the name of developing our self-driving solution.

RELATED: Visit the Emerging Talent LinkedIn Page

The Future of Emerging Talent at Torc Robotics

Looking ahead, we’re envisioning that our new initiative will be a key driver of our growth strategy. Talent pipelines and software engineering internships like the ones we’ve developed with KIT will continue to be a crucial component, ensuring a steady stream of top-tier talent from across the globe. Alongside this strategy, we’re focusing on inclusivity, adaptability, and skills-based hiring across the board. We’re dedicated to attract and retain the best talent that the self-driving engineering world has to offer, driving our technology and our company forward in a competitive and dynamic industry.

Torc Takes Texas: Bringing Autonomous Trucking to Ft. Worth, Austin, and San Antonio

Torc Takes Texas: Bringing Autonomous Trucking to Ft. Worth, Austin, and San Antonio

If first responders and government officials can’t make it to Torc, Torc will bring autonomous trucking technology to them, especially in Texas!

Torc took to the Texas highways May 6 – 9, 2024, visiting locations in Ft. Worth, Austin, and San Antonio. With a traveling, custom-wrapped event trailer as our location on wheels and our ADS-ready Freightliner Cascadia, Torc hosted over two hundred first responders, transportation experts, and the public safety community. The week was filled with amazing conversations about autonomous trucking and Torc’s First Responder Interaction guides, while sharing Torc’s commitment to safety and innovation.

Torc’s First Responder Guide provides information on how first responders can safely interact with our trucks. More information about our First Responder Guide can be found here.

The tour was an important opportunity to share Torc’s vision and provide attendees with a first-hand experience with our innovative long-haul trucking technologies. Guests were able to climb into the truck cab, view the controls, and learn about the sensors, cameras, and software that encompass our autonomous driving system. Importantly, it provided education about the future ahead, answering questions, offering facts, and explaining how autonomy will help shape freight logistics.

Check out the video below for a recap of the event and more information from Michelle Chaka, Torc’s Senior VP of Safety and Regulatory.

In Case You Missed It:

Be sure and check out Michelle Chaka’s webinar on Safely Delivering Autonomous Trucking Solutions

 


Torc to Present Nine Papers at CVPR 2024

Torc to Present Nine Papers at CVPR 2024

Driving Autonomous AI with Torc’s Head of Intelligence

This summer, Torc’s Head of Artificial Intelligence, Felix Heide, and his team of both Princeton University and Torc colleagues will present an extraordinary total of nine papers at the IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR). Featuring information on geometry reconstruction, generative method, learning techniques, novel datasets and more, Felix and his team will exhibit their core competencies in researching and creating AI tools and techniques for self-driving artificial intelligence and beyond.

Torc at IEEE/CVF CVPR Conference

As one of the primary events in the field of computer vision, CVPR brings leading researchers, industry professionals, academics, and more, to a weeklong conversation about the latest findings in the world of computer vision and pattern recognition. With its main exhibition floor, presentations, and expert attendees, CVPR offers all levels of computer science professional with an opportunity to share their cutting-edge research and collaborate within the community. The IEEE/CVF CVPR Conference serves as the perfect backdrop for the innovative research Torc is spearheading.

The nine papers at CVPR 2024 cover a wide range of topics, each offering unique insights and contributions to the field. From advancements in neural rendering to new types of lidar, Felix, joined by his Princeton and Torc teams, has developed comprehensive content that reflects the depth and breadth of the industry’s expertise. Their work showcases the latest developments in computer vision and pattern recognition and indicates the ongoing progress of autonomous trucking technology.

Innovating Freight with AI

The significance of this research extends far beyond the confines of academic discourse. By pushing the boundaries of AI and machine learning, this work has the potential to revolutionize the autonomous driving industry and reshape the way we interact with technology. At Torc, these contributions help us pave the way for safer, more efficient freight systems that will benefit fleet professionals, everyday consumers, and all highway users.

As we move forward, AI research points us towards exciting new possibilities for collaboration and innovation. As academia, industry, and other research organizations come together to tackle the challenges of tomorrow, conferences like CVPR play a crucial role in fostering dialogue and driving progress. By sharing their insights and expertise, researchers like Felix and his team can shape the future of AI and propel us towards a world where driverless trucks enhance our lives in ways we’ve only begun to imagine.

These contributions not only highlight the cutting-edge research happening at Torc Robotics but also underscore the validity and potential of autonomous technology. As we continue to innovate our automated truck technology, our team’s contributions propel us to drive the future of freight in new and innovative ways. For our team, self-driving AI isn’t just a future concept, but a tangible reality that will make our world safer, faster, and stronger.

 

About Felix Heide, Torc’s Head of AI

Felix Heide is an industry leader in both artificial intelligence and autonomous technology. His journey to becoming an expert in general artificial intelligence, self-driving AI, and machine learning began long before his time at Torc, ranging from his first internship with NVIDIA Research in 2013 to his current role leading autonomous trucking development.

Felix is an Assistant Professor at Princeton University, Head of AI at Torc Robotics, and founder of the self-driving vehicle startup Algolux (now part of Torc). He is researching the theory and application of computational imaging and computer vision systems. Exploring imaging, vision, and display systems end-to-end, Felix’s work lies at the intersection of artificial intelligence, computer graphics, and computer vision.

He received his Ph.D. from the University of British Columbia, his undergraduate degree from the University of Siegen, and was a postdoc at Stanford University. His doctoral dissertation won the Alain Fournier Dissertation Award and the SIGGRAPH outstanding doctoral dissertation award. He won the NSF CAREER Award 2021 and the Sony Young Faculty Award 2021. He was named a Packard Fellow in 2022 and a Sloan Research Fellow in 2023. Felix was named SIGGRAPH New Significant Researcher in 2023.

 

 


This article is part one about Torc’s presence at CVPR this year. Look for more news about the CVPR event in June.

Lane-Keeping in Self-Driving Trucks: Precision and Trust

Lane-Keeping in Self-Driving Trucks: Precision and Trust

Across all the features that self-driving technology has to offer, we might think of lane keeping as one of the most basic features possible. However, lane keeping is a complex behavior that relies on multiple components, sensors, and procedures to complete safe driving behaviors. In self-driving technology, precision is everything, making lane keeping a foundational necessity that underscores the safe and efficient operation of robotic trucks.

What is lane keeping?

Lane keeping is a critical driving functionality that ensures a vehicle stays within its designated lane on the road. Many newer consumer cars and commercial semi-trucks have some form of autonomous lane-keeping system programmed in, albeit there are several nuances and differences between types of lane-keeping systems, such as:

Lane Keep Assist (LKA)

Lane Keep Assist is a feature that can be toggled on and off on most vehicles. It typically works via camera, allowing the LKA to “see” the lane lines and nudge your vehicle within the lane lines when it begins to drift. However, because it’s camera-based, this feature may struggle to perform in muddy, snowy, or especially rainy conditions.

Lane Keep Assist is sometimes confused with Lane Departure Warning, which alerts drivers via haptic feedback, audible alerts, and sometimes indicator lights, if they’ve begun drifting out of the lane. Unlike other forms of lane-keeping systems, lane departure warning won’t correct the vehicle’s path. Instead, its job is to inform the driver that the vehicle is exiting the lane.

Lane Centering Assist (LCA)

Lane centering, sometimes called autosteer, takes LKA a step further. This feature is typically part of a vehicle’s adaptive cruise control, wherein a vehicle performs most highway behaviors itself while under human supervision. Lane centering is an active technology that keeps a vehicle in the center of its lane and can typically be turned on and off.

Today, many Class 8 trucks come equipped with various forms of Lane Keep Assist, Lane Centering Assist, and Adaptive Cruise Control. Aside from making drives safer for truck drivers and other highway users alike, these features can adjust throttle inputs and gear ratios for more efficient driving behaviors. By utilizing these features, drivers can optimize the amount of fuel their equipment consumes, reducing costs across the board.

Why is lane keeping important?

Lane keeping plays a foundational role in ensuring the safe and efficient operation of any vehicle, including our autonomous trucks. By enabling our robotic trucks to steadfastly maintain their designated lanes, we’re not only addressing a core competency in highway navigation but proving that our technology can be a safe foundation for a self-driving system.

Lane-keeping is important because of its impact on safety, but there are a few other reasons why we focus on this behavior as one of the most integral in safe-driving technology.

lane keeping

 

Traffic Flow and Predictability

When vehicles stay within their designated lanes, it reduces the likelihood of swerving and abrupt lane changes. When we humans learn to drive, we learn that being a predictable driver means being a safe driver.

Our autonomous technology is no different. In order to reduce the likelihood of traffic accidents and promote smoother traffic flow, we must ensure that other drivers are able to anticipate what our self-driving truck is going to do at all times. Whether that means keeping a consistent, steady pace within one lane or using an indicator light to shift lanes, predictability should be at the forefront of all lane-keeping behaviors.

Efficiency

By staying within the given lane, vehicles maximize the use of available road space, allowing more efficient traffic flow. During peak hours, when space is at a premium, this can reduce delays, avoid bottlenecks, and make it easier for vehicles to travel at a consistent speed throughout their journey.

How do self-driving cars and trucks stay in their lanes?

Self-driving trucks and self-driving cars stay in their lanes via cameras, Global Navigation Satellite Systems, LiDAR (or Light Detection and Ranging sensors), and more. Thanks to the work of autonomous driving engineers, our self-driving semi-trucks’ perception suite can recognize lane markers, interpret them correctly, and communicate this information to the rest of the system. From there, the autonomous driving system can utilize the information to maintain a set speed and keep watch on the distance between it and the vehicle in front of it.

There’s a common misconception that driverless cars and driverless trucks rely on lane markers alone to make sense of the path before them. While this used to be the case for very early self-driving cars, our autonomous abilities have advanced to grand new heights. Today, lane markers (and the cameras that “see” them) are just one piece of the puzzle.

Self-driving vehicles also utilize radar, which is sometimes found in Lane Keep Assist programs that we have in our day-to-day cars. Radar adds an additional safety component to lane navigation. Using radio waves to detect objects like other cars and traffic cones, radar helps paint the picture of what the driving environment looks like. In the same vein, mapping allows a self-driving vehicle to utilize historical information about the road to navigate in conjunction with the other tools in its toolbox. These two tools work with lane marker detection to assess the environment, calculate the safest possible behavior, and execute that behavior.

Lane Keeping and Robotic Trucks

As proponents of safe and sustainable self-driving practices, our autonomous driving system keeps in line with regulatory and industry best practices throughout all lane keeping behaviors. Aside from its impact on safety, proper lane keeping allows us to operate predictably to drivers on the road around us, prove our product’s viability, and promote a safe self-driving future.

As we forge ahead with our driverless trucking development, we will continue to innovate, collaborate, and lead the way in advancing our autonomous driving system. Through ongoing research, development, and collaboration with our stakeholders and partners, we will further enhance our lane-keeping capabilities to meet the evolving needs and expectations of the industry and the public. Together, we’re driving the future of freight.

 

 

Understanding the Levels of Autonomy: 3-4-5