By John Marinaro, Director of Operation Safety & Testing
When people ask me about the self-driving trucks we are developing at Torc with Daimler Trucks North America, they generally ask one of three questions: 1) Are they safe? 2) How can you predict the unpredictable? and 3) How do you know they are safe? These are good questions, especially considering that Torc and Daimler have both said we won’t commercialize a Level 4 self-driving truck until we’re certain it is safe. What most people miss, however, is that safety practices for self-driving trucks — and for human drivers — should emphasize avoiding problems or incidents more than reacting to them.
Let me explain by first stating the obvious, which is that self-driving systems are not perfect. As a former NASA safety engineering executive, I understand that we cannot completely eliminate risk. In safety, our job is to understand and mitigate risk as much as possible. There are issues and parameters that we know we must understand. There are also issues we don’t even realize we don’t know, also called unknown unknowns. This is certainly the case for self-driving vehicles.
Mitigating the Risk of the Unknown
At Torc, we are building an exemplary virtual driver. Like the best human drivers, our driver can make incredibly good decisions quickly in a crisis. Exemplary drivers – both human and virtual are critical to on-road safety. About 77% of all traffic accidents are caused by driver error. These incidents and accidents are when drivers, for many reasons, are not following established safety protocols and best practices. Our virtual driver is designed with these best practices in mind – to react predictably and consistently.
Are self-driving trucks safe? Autonomous driving systems do have some technical advantages to human drivers. As mentioned, autonomous driving systems don’t get tired or distracted. Wide sensor coverage on the vehicle provides continuous and comprehensive detection of moving and stationary elements at all times – so that’s a huge reduction in blind spots that human drivers are subject to. Torc engineers are factoring in situations that are leading indicators of accidents along with specific data about high-risk areas.
We also build in detailed strategies to implement in advance of any developing risk situations. Many of these same strategies are taught to professional CDL drivers in defensive driving training programs. For example, the Take 5 System from the Smith System Driver Improvement Institute teaches drivers to aim high in steering, get the big picture, keep your eyes moving, leave yourself an out and to make sure they see you. All of this is geared toward accident avoidance, and these guidelines are industry-accepted best practices for tractor trailer drivers. Self-driving trucks can do all of this and much more.
I would like to focus on the fifth guideline from Smith for a moment: leave yourself an out. If you don’t have an escape path, then you’ve got nowhere to go if an unexpected situation happens on the road. We are also integrating the perspective that our trucks constantly face drivers who do not appreciate what it takes to drive a 40-ton tractor trailer down the road at relatively high speeds. There are physical limitations to maneuvering a large truck — such as stopping speed and turning radius — that aren’t present in passenger cars and an exit path should take these factors into account.
So how do we manage risk for unpredictable drivers on the road? How do we predict the unpredictable? We can’t control those around us, but we can accommodate them. Fortunately, we have data from studies on what increases the probability of an accident. Avoiding unnecessary lane changes, for example, will reduce chances of an accident by 12%. Of course, sometimes it’s safer to change lanes when drivers face lane closures and left exits, but avoiding accidents and close calls is a matter of best practices supported by safety data. At Torc, safety data like this allow us to program our software with information that would take a human operator decade of experience to know and master. For example, we can inform the autonomous truck to “pre-position” in a lane when a traffic situation shows pending trouble, avoiding the need for a fast change.
Some people are concerned about software and hardware failures in self-driving trucks, and at some point there likely will be failures. We are building in redundancies and fault tolerance in our design, to help manage what we cannot prevent and plan for failing safe. For this, we also take a page from NASA and aeronautics and have a “hot spare” at the ready to take over a degraded or failing system for example, adding redundancies to safety-critical systems.
Defining the Safety Envelope
Let’s also consider the driving safety envelope. Torc is defining specific driving behaviors for different traffic and environmental conditions that keep the vehicle operating within a high level of safety. This is critical to on-road safety because data show that eliminating just one factor of a developing risk event can reduce the probability of an accident by 95% or more. We classify the safety zones by color–green for safe, yellow for less safe, and orange for risky and red for dangerous zones. When we are taught to drive an automobile, for example we are told to allow a 3-second distance from the vehicle in front of us. For trucks, it’s 5-7 seconds, because it takes them longer to stop. Following the above distance guidelines would keep drivers in the green — where we want to live — at least 90% of the time. But this is not how people generally drive. A quick trip around D.C., for example, would reveal that people spend most of their time in the red zone. Consequently, there are accidents every day. Staying in the green zone would reduce accidents by more than 75%. Operating in the red zone is unsafe. You have no margin and a high chance of being forced to execute a hero response to avoid an accident.
Autonomous trucks hold the safety envelope advantage, both due to the large number of simultaneously reporting sensors and the ability to precisely measure location and act accordingly. Sensors allow the system in a self-driving truck to detect exactly where everyone else on the road is at once. It doesn’t need to take the time to look around in different mirrors sequentially, as human operators must. Moreover, the self-driving truck does not adopt human behaviors of impatience, following the crowd, or developing aggressive emotions if there is trouble on the road.
Changing lanes is a high-risk event for trucks as well as cars, and an industry guideline for changing lanes is called Take 10, which means to signal for 3 seconds and then take 7 seconds to complete the lane change. Add to this speed reduction guidelines, such as reducing speed by 5 mph for dense traffic, curves or weather conditions, and you already have an impressive package of defensive driving guidelines that greatly reduce margins for errors and mitigate risks of accidents and close calls.
We use these guidelines and others to define the behaviors of our self-driving trucks, with the target of operating in the green zone of the safety envelope as much as possible. Our goal at Torc is to lead the way in operating trucks safer, more effectively and more efficiently than most human drivers, which we hope will reduce risk and save lives. This is all possible because the driving behaviors we are talking about can be implemented consistently with the right programming.
Just as human drivers learn from experience, our self-driving trucks will gain experience. However, people gain experience one person at a time, whereas our self-driving trucks benefit from collective learning. Those sensors and computes that help the trucks perceive the situation around them can also store the data, or record the data, in case of an incident or if an extreme response is needed. We analyze all such occurrences, determine the appropriate response and update the software across the fleet. We also plan for where there is an unknown, for example, programming trucks to safely come to a stop in the case of a situation the system is not prepared to handle.
The Future of Safety on the Road
How do I know self-driving trucks are safe? Because we are building the most experienced, exemplary driver possible, supported by best-in-class hardware and computes, advanced technology, experienced truck drivers, road safety data, and industry-standard best operating practices. I imagine that before we are done, our knowledge can help teach human drivers how to be safer on the road.
Join Our Team
Torc’s Safety and Mission Assurance team is using a data-driven approach to developing self-driving semi-trucks. If you’d like to support our mission of helping to make the roads safer, apply today to join our winning teams.
The freight industry is on the cusp of several technological advancements to improve efficiency, safety and transport as a whole. Two big revolutions are being prepped for at the same time: autonomous driving software and battery electric power. However, what does one have to do with the other? While there is some crossover, self-driving semi-trucks and electric battery semi-trucks have different considerations right now in the current marketplace.
Semi-trucks are freight-focused vehicles used for both long-haul journeys across the interstate and ‘last-mile’ trips between distribution hubs and final destinations. They carry life-saving medicines, groceries, clothes, and so much more, across the nation. As self-driving electric trucks and diesel-powered 18-wheelers ship these goods, there are different ideal use-cases for both dependent on range and infrastructure.
The Current State of Electrification
Today, the electric vehicle we’re all most familiar with is likely the consumer car. Several car brands now feature some form of hybrid or fully electric vehicle, enabling many everyday drivers to join the electric revolution. But are there electric semi-trucks? And if so, are electric semi-trucks feasible?
There are – and there’s a vast range of them. Your average electric semi-truck is a zero emissions model with an average range of 200 miles (depending on vehicle configurations, but electric semis with 350 miles of range are in production) when fully charged. Given its mileage, these kinds of trucks are ideally suited for short-haul routes that allow for depot-based charging.
Because our supply chains run on tight timelines and high consumer demands, these semi-trucks need to be charged relatively fast. This requires far more power than the typical fast chargers meant for consumer vehicles. In the same vein, they need significantly more real estate in which to park while they wait for their superchargers to operate.
Range and infrastructure continue to be improved upon in electric 18-wheeler development. Many semi-truck companies are working alongside partners both in the private sector and the government sector to tackle the infrastructure challenge. In the same vein, electric semi-truck designers are thinking ahead. For instance, most electric semi-truck designers focus on “opportunity charging”, meaning that these industrial batteries are charged for short bursts rather than all at once; this begins to address the charging challenge. With new grants, listening sessions, and plans being created every day, we’re moving towards an electric future that’s sustainable for people and places alike.
The industry has also been answering the emissions question with significant results. In 2021, emissions from the transportation sector (including delivery trucks, long-haul freight, and other logistics vehicles) made up 20% of the overall emissions in the United States. As electric Class 8 trucks move into mass production and eventual mass roll-out, that emissions number is expected to continue falling from its 2019 number of 26%.
Although the initial cost of electric cars and electric 18-wheelers is typically higher than the gasoline or diesel counterpart of these vehicles, the total cost of ownership is projected to be lower. Fuel savings are the most obvious cost saving vertical, but these vehicles also typically come with several telematic solutions, which can boost efficiency by minimizing hard braking, providing on-board diagnostics, and more. Overall, electric 18-wheelers do have promising future prospects even in this technology’s early stage.
Autonomy Outlook: Gas vs. Electricity
There are a few different factors needed to consider the gas vs. electricity debate in the autonomous truck sector. Namely, intended use cases.
At Torc, our target use case centers around the long-range, or any journey that exceeds 250 miles. We’re laser-focused on creating software that autonomously drives semi-trucks to-and-from shipping hubs across the country, meaning that long-haul journeys are at the forefront of everything we do. In the same vein, we’re proud to be partnering with Daimler Truck on developing a fully autonomous Freightliner Cascadia: an advanced, diesel-powered vehicle that is purpose-built for an autonomous driving system.
Given the discrepancy between our long-haul needs and the typical electric truck range, Torc’s vision for the immediate future doesn’t yet include electric models. However, that’s not to say that it’s not part of our eventual future. As our world moves towards green practices and electric vehicles become more and more common, we’re open to the possibility that electric 18-wheelers may replace diesel 18-wheelers altogether.
In the meantime, we are still looking ahead to how we can maximize fuel efficiency. Several studies have shown the potential of autonomous trucks to increase fuel efficiency. Driving at a more consistent speed and reducing the amount of excessive braking or acceleration improves fuel economy. The U.S. Department of Transportation is currently researching the potential of autonomous trucks to determine how they could improve fuel use in the future.
Innovations in Efficiency: Hydrogen Fuel Cells
While electric trucks may not be suitable for long-haul freight, hydrogen fuel cell technology may provide a different story entirely. This research is still being carried out, but it has some interesting prospects for the world of autonomous and automotive tech alike. Once deployed, it could be a fuel source appropriate for long-haul autonomous trucking.
A fuel cell is a highly efficient energy conversion device. In the case of hydrogen fuel cells, these devices combine oxygen and hydrogen to generate electricity. Vehicles with fuel cells are still electric vehicles, albeit they don’t need to be charged. Instead, they utilize hydrogen fuel to make their journeys across city streets and highways.
Many autonomous truck companies are working on various forms of hydrogen fueling. From liquid hydrogen to carbon-fiber reinforced vehicle tanks, innovation is happening in this sphere at a rapid rate. At Torc, we’re watching these developments closely in anticipation of ushering forth this new era of automotive excellence.
Electric Semi-Trucks in 2023 and Beyond
Electric vehicles are sure to be part of the way we explore new ways of moving passengers and freight alike. While we’re only just beginning to see a world where electric semi-trucks are for sale, this new tech is growing to new heights every day. We’re excited to see where our autonomous journey and the ongoing development of electric freight trucks takes the automotive industry as a whole.
This past week, ‘Trucking Forward’ hosts Tim and Adam sat down with Dr. Charlie Reinholtz, an esteemed academic and professor in the automated vehicle space. From his time spent driving students across the country to enter the DARPA challenge to fostering a problem-solving attitude, Dr. Reinholtz shared his story in this upbeat episode.
Since 1983, Dr. Reinholtz has served as a professor and advisor to students pursuing self-driving vehicles as part of their career path. Dr. Reinholtz shared the story of how he began this journey.
“In 1995, we entered our first Intelligent Ground Vehicle Competition… And we did well in the design competition. We didn’t do very well dynamically, but we had a real great collection of students that it became a passion for me and the students,” said Dr. Reinholtz.
Dr. Reinholtz emphasized the significance of autonomous vehicle competitions as a means of providing hands-on learning opportunities and preparing students for real-world challenges. Dr. Reinholtz recounted his involvement in various student competitions, such as the Intelligent Ground Vehicle Competition (IGVC), the Student Unmanned Aerial Systems Competition, and the DARPA Challenges. Over the years, Dr. Reinholtz and his teams at Virginia Tech consistently performed well in the design competition at IGVC, achieving more than half of the wins in the competition’s history.
From there, the conversation shed light on the importance of hands-on learning, collaboration, and innovation in shaping the future of the industry. Dr. Reinholtz’s passion for working with students and his contributions to the field have left a lasting impact on the academic world, the industry of autonomy, and even engineers at Torc.
At these competitions, students and faculty members form cohesive teams, working together toward a common goal. The camaraderie and shared experiences create a unique environment where faculty and students are equal contributors. Dr. Reinholtz expressed his admiration for students’ dedication and acknowledged their tremendous efforts, even when academic credit did not fully reflect their contributions. Tim Zuercher, VP of Engineering at Torc, agreed.
“Coming in and working in [the competition] culture, it’s the collaboration. It’s not just that you’re fixing it, it’s like we’re all fixing it. Everybody’s on the hook for the same thing, and the spirit that brings,” added Tim.
Dr. Reinholtz attributed the success of his teams to meticulous preparation and attention to detail. In competitions, unexpected challenges often arise, and teams must think on their feet and devise creative solutions. Dr. Reinholtz emphasized the importance of doing thorough homework and being fully prepared. This includes anticipating potential issues, developing robust designs, and making persuasive presentations. The ability to adapt and find “good enough” solutions amidst the chaos of competition is a valuable skill that prepares students for autonomy’s dynamic nature.
The conversation also touched upon the impact of these competitions on student motivation. Dr. Reinholtz stressed the significance of establishing a caring and supportive environment where students feel appreciated. By recognizing their hard work and providing the necessary resources, faculty members can inspire students to go beyond their academic requirements. Dr. Reinholtz’s dedication to mentoring and supporting his students has resulted in countless success stories, with graduates making significant contributions to the industry.
“I really do believe that the people are a lot more important than having the talent,” he shared. “I could see that I was working with these students, and that if I could just keep them together as a group, like what happened with Torc… they’re going to be successful. Maybe there are going to be some ups and downs, but the people are just too talented and too hardworking. You can’t fail in the long run when you have that kind of ability and motivation.”
The discussion concluded with a reflection on the technological advancements since Dr. Reinholtz’s early involvement in autonomous vehicle competitions. While the technology of that era may seem primitive compared to today, the accomplishments were still remarkable. The DARPA Challenges, in particular, presented significant milestones in the field, with teams racing autonomous vehicles across the challenging Mojave Desert. Dr. Reinholtz commended the progress made in the industry and credited the dedication and commitment of the students he had the privilege of working with.
This past week, FreightWaves held its annual Future of Supply Chain convention in Cleveland, Ohio. At this event, attendees had the opportunity to witness the digital transformation of various companies in the logistics and trucking industries, including leading self-driving truck company, Torc Robotics.
Across a host of events, panels, and one-on-one engagements with convention goers, Torc brought together some of the greatest minds in transportation, logistics, and supply chain industries. Whether convention goers were seeking out information about the self-driving future or current trucking outlook, Torc Robotics had insights to share.
What the Truck?!?
During the convention, Torc’s Senior Analyst of Corporate Strategy, Frank Mabry, appeared on FreightWaves’ popular podcast, “What the Truck?!?” hosted by Timothy Dooner. Frank delved into the concept of Class 8 autonomous trucking, explaining how these vehicles will operate and shedding light on Torc’s cutting-edge technology. Torc Robotics, in partnership with Daimler Truck North America, is actively developing self-driving truck software designed to handle complex real-world scenarios, adapt to changing environments, and ensure precise vehicle control.
“It’s an exciting time,” Frank said. “We’re working on cutting edge technology, something that’s never been done before.”
‘Truck Tech’ with Alan Adler
Frank also sat down with Truck Tech’s Alan Adler, sparking insight into the autonomous revolution. He emphasized Torc’s approach of building autonomous trucks from the ground up, differentiating them from traditional trucks. Torc’s initial product, a Level 4 autonomous Freightliner Cascadia, is purposefully designed for autonomous applications, incorporating safety redundancies to ensure reliability.
“We’re building the truck from the ground up,” Frank began, explaining the goal for Torc’s initial product: a Level 4 autonomous Freightliner Cascadia. “If you went in and ordered a Freightliner Cascadia and a Torc-powered Freightliner Cascadia, it’s absolutely two different trucks. Ours is designed specifically for autonomous applications. It’s two different chassis, will be a 100% safe, if one system fails another part takes over.”
Torc’s collaboration with Schneider and C.R. England further demonstrates the seamless integration of self-driving truck companies and freight entities, with the aim of achieving consistent drives and minimizing freight loss during transit. Alan and Frank discussed this collaboration throughout their conversation.
“It’s one thing to have all the knowledge about what’s happening in the cab,” Alan prompted. “But your freight component is big.”
“Absolutely!” Frank replied. “We’re thinking you’re gonna have more of a consistent drive, more consistent arrival and less freight loss from transit, if we have these kinds of pilots early on.”
The Torc team also joined FreightWaves Radio’s host, Grace Sharkey, to dive into the vast world of autonomy. This time, Frank Mabry was joined by Nick Elder, Torc’s Director of Strategy. Together, they talked through what the impacts of autonomy could potentially have on the truck driver population.
Nick and Frank shared that it’s important to note that the adoption of autonomous trucks is likely to be a gradual process, allowing time for the industry and workforce to adjust and adapt to the changes. In the same vein, regulations on self-driving vehicles vary drastically from state to state and even city to city. As the greater conversation about driverless trucks develops, it will take some time for municipalities, states, and federal government officials to collaborate on the best solution for each unique scenario.
The FreightWaves event offered engaging discussions, rapid-fire demos, interactive sponsor kiosks, and other exciting activities. With over 70 experts in the freight industry, we had the chance to engage in sessions with our partners, peers, and vendors about the future of our industry. With every relationship we develop with our trucking and logistics counterparts, we get one step closer to an autonomous future.
As with all events we attend, our goal is to educate the greater freight community about the possibilities autonomy has to offer. Driverless trucks have the potential to greatly enhance our daily lives in numerous ways. They can reduce shipping expenses, generate improved job opportunities for transportation and freight experts, and enable trucking companies to run their fleets with greater efficiency. With this innovative technology, our supply chains will reach unprecedented levels of dependability and performance. From heightened efficiency to the safety prospects, automated 18-wheelers are going to change our world for the better.
Need a new podcast? Interested in autonomous technology, trucking, and all the ways these two industries connect? Give our “Trucking Forward” podcast a follow. Hosted by two long-time Torcr’s, every episode will bring dynamic discussions with software engineers, freight and trucking experts, and industry creators and innovators. From Torc’s autonomous advisory council members to trucker advocacy non-profits, our roster of guests will apply their unique perspectives to topics like intermodal transportation, regulatory processes, levels of autonomy, software testing situations, and more.
Meet Tim and Adam
Tim Zuercher is the VP of Engineering for Autonomy, where he leads the development of perception, localization, mapping, behaviors, planning, and control algorithms for Torc’s Virtual Driver. Joining Torc just before Torc became an independent subsidiary of Daimler Truck in 2019, Tim has served in multiple roles from Software Engineer to Technical Product Director of the Virtual Driver. Prior to Torc, he was at Embry-Riddle Aeronautical University where he helped grow the robotics research program while developing autonomy algorithms and platforms for land, sea, and air. Tim holds a B.S. in Aerospace Engineering and an M.S. in Mechanical Engineering.
Adam Shoemaker currently holds the role of Chief Architect at Torc, where he works across the organization, weaving the threads of Torc’s solution into a working tapestry, while mentoring teams and individual contributors as a technology evangelist. Joining Torc in 2016, Adam has served in multiple roles from Software Engineer to Technical Director. Prior to Torc, he was at Virginia Tech where he focused on control theory, state estimation, planning, localization, mapping, and perception, and participating in various research grants focused primarily on unmanned ground robotics applications. He also has the distinction of hiring Tim, from a phone interview alone. Adam holds a B.S. and an M.S. in Mechanical Engineering.
New episodes will be released every other Tuesday. Subscribe now on your favorite podcast platform.
The contest encourages high school juniors and seniors to imagine and discuss a future that includes automated vehicles and write about what this technology could mean for their communities, with a choice of three provided essay prompts related to AV technology and its societal effects. The winning essays were selected from over 100 submissions, and a committee of experts from the AV ecosystem scored the student essays.
The winners of the 2022-2023 PAVE Essay Contest in the Albuquerque, N.M. area are:
“Autonomous vehicles offer an opportunity for us to improve road safety, to provide new mobility options for our communities, and to make our transportation system more efficient, more equitable, and more sustainable – but at the same time, there are new challenges that we need to think through,” said PAVE Executive Director Tara Andringa, quoted in the PAVE press release. “The PAVE Essay Contest encourages young people to think about these new technologies and share their thoughts about the opportunities for societal impacts as well as how we can address challenges that could arise. We were thrilled that so many students participated in the contest, and we are excited to congratulate the winners!”
The newly inaugurated annual essay contest will be open to students in selected nationwide locations. The three locations for this year’s contests were Washington, D.C., Albuquerque, N.M., and Athens and Vinton Counties in Southeast Ohio. In each location, companies and organizations will sponsor the contest and donate the scholarship funding: the Washington, D.C., contest was sponsored by STEER Tech; the Albuquerque contest was sponsored by Torc; and the Ohio contest was sponsored by Transportation Research Center, Inc. and DriveOhio.
C.R. England and Torc Robotics will work together on long-haul autonomous trucking pilots
BLACKSBURG, VA – May 9, 2023 – Torc Robotics, an independent subsidiary of Daimler Truck AG and a pioneer in commercializing self-driving vehicle technology, today announced its strategic collaboration with C.R. England, one of North America’s premier transportation companies. Torc and C.R. England will implement a pilot program leveraging C.R. England’s temperature-controlled loads and Torc’s fleet of Level 4 autonomous test trucks for long-haul applications. The collaboration will serve as an expansion for Torc into refrigerated freight.
C.R. England and Torc are excited to participate in this joint pilot, which will provide select customers with temperature-controlled capacity and world-class service. Information from the pilot will include unique insights, and will help guide the development and ongoing commercialization of autonomous trucks for long-haul applications. Initial planning will begin mid-2023, with on-road tests soon after.
“Torc is thrilled to be partnering with C.R. England to better improve long-haul trucking safety for one of the premium service providers and largest refrigerated carriers in the nation,” said Peter Vaughan Schmidt, Torc Robotics CEO. “The data derived from the pilot will contribute to our safety and validation efforts and use cases for autonomous trucking.”
“C.R. England is excited to announce our partnership with Torc for pilot activities on level 4 autonomous test trucks. We believe this innovation will eventually provide the ability to expand our network safely, with high levels of service to our customers, all while enhancing the quality of existing driver jobs,” says Chad England, C.R. England CEO. “Specifically, by adding autonomous lanes to our network, we can expand our customer offerings and create more structured jobs for drivers at both ends of autonomous runs. Torc’s deep integration with Daimler Truck AG makes our two organizations a perfect fit for piloting this new technology.”
The pilot program with C.R. England is Torc’s second announced carrier pilot. This news comes on the heels of Torc’s recently announced acquisition of Algolux for its award-winning intellectual property and expertise in computer vision and machine learning.
Torc’s deep integration with Daimler Truck AG makes our two organizations a perfect fit for piloting this new technology.
Chad England, C.R. England CEO
ABOUT TORC ROBOTICS
Torc Robotics, headquartered in Blacksburg, Virginia, is an independent subsidiary of Daimler Truck AG, a global leader and pioneer in trucking. Founded in 2005 at the birth of the self-driving vehicle revolution, Torc has 17 years of experience in pioneering safety-critical, self-driving applications. Torc offers a complete self-driving vehicle software and integration solution and is currently focusing on commercializing autonomous trucks for long-haul applications in the U.S. Torc operates test facilities in Albuquerque, New Mexico, and engineering offices in Austin, Texas, and Stuttgart, Germany. Torc’s mission is saving lives with autonomous technology, which incorporates reducing highway deaths, enabling critical supplies – including medicines and foods – to reach every community in a timely manner, and helping the transportation industry increase fuel economy, uptime, and capacity.
ABOUT C.R. ENGLAND
Founded in 1920, C.R. England is headquartered in Salt Lake City, UT and is one of North America’s premier transportation providers. The company is an industry leader in Dedicated, Over-The-Road, cross-border Mexico, Intermodal, and Logistics services. C.R. England has been regularly recognized for management excellence. This year, the company was recognized by Newsweek as one of ‘America’s Greatest Workplaces for Women,’ and ‘America’s Greatest Workplaces for Diversity.’ Additionally, C.R. England was recently honored by The Wall Street Journal as a ‘US Best Managed Company,’ by Glassdoor with their ‘Top Places to Work’ award, and by Achievers with their ‘50 Most Engaged Workplaces™ Award.’ C.R. England is committed to giving back to the community by fighting childhood hunger. With each load delivered, the company feeds a child, with the goal of feeding one million children per year.
Torc Robotics, an independent subsidiary of Daimler Truck NA, headed west for the Advanced Clean Transportation (ACT) Conference and Expo at the beginning of May 2023. The four-day conference focused on the trends and technologies transforming commercial transportation, and as such, autonomous trucking took a front seat. Attendees and exhibitors chose from over 30 sessions and toured 300 booths, including Torc at booth 6957.
Nick Elder, Torc Director of Corporate Strategy, spoke twice at the event on Wednesday afternoon, May 3. First, he held a Tech Talk on the Expo stage, elaborating on the relationship between Torc and DTNA, and the Torc mission to arrive at Level 4, driver out, autonomous operation in the market.
“One of the natural questions is always what’s the timeline look like for this. We’re looking at these advanced technologies and autonomy is an incredibly challenging proposition,” said Nick. “And we’ve been clear since the very early days: We’re going release a product when it is safe to do so, and that means rigorous validation. And that that is going to take time to accomplish.”
“So what is Torc’s vision? When we think about the pillars that we want stand on, as we look to bring automation into the Class 8 space, first and foremost, bringing value to customers, in a safe way. We want to create a safer solution that will ultimately bring value to freight networks, to carriers, and to the end customer, the shippers,” Nick continued. “We believe that to do that it’s absolutely imperative that you collaborate with partners. So that means partnerships with OEMs like Daimler, it means partnerships with carriers as well to make sure we’re developing the right product and that it can integrate into the freight ecosystem.”
Additionally, Daimler Truck NA president and CEO and Torc Board Member John O’Leary opened up the Expo as a keynote speaker. DTNA was also a presenting sponsor of ACT Expo 2023 and hosted booth 6440.
One of the reasons why we appreciate the relationship we have with Torc is because you bring us together, and we can have these conversation. We can tackle some but not all of the challenges together, because we’re all going to deal with the different ‘what if’ scenarios.
Matt McLelland, VP of Sustainability and Innovation, Covenant
Later on Wednesday, Nick took part in a breakout session entitled “Autonomous – Developments in Piloting and Scaling Commercial Autonomous Vehicles.” Moderated by Chris King, Senior Vice President, eMobility, Siemens, the other panelists included Michael Wiesinger, Vice President of Commercialization, Kodiak Robotics; Mike Plasencia, Managing Director of RyderVentures and New Product Strategy, Ryder System, Inc.; and Shawn Kerrigan, Chief Operating Officer and Co-Founder, Plus.
Speaking as part of the panel, Nick elaborated on one commonality between Torc and the other participants in regard to autonomous vehicle operational design domains. “When we look at these level designation for autonomy, I think we’re all going to be focused on that L4 space. So it’s going to have a defined domain. And that really references the type of infrastructure you can handle, what type of roads you can handle, the environmental conditions that you can handle,” said Nick.
“If a truck is dispatched from a location and during its journey, midway in transit, it starts to snow or rain — beyond the capabilities of that system — it’s going to be critical that the system is capable of understanding that it’s now going outside of the domain in which it was designed to operate. And it will still need to find itself in a safe state,” he continued. “It’s going to have to know that it is beyond those limits and make itself safe.”
Torc looks forward to returning to ACT Expo in 2024. For more information about Torc and the presentations shared at the event, contact press@torc.ai.
The level of engagement and commitment, not to mention the record-setting attendance, at the ACT Expo this week makes it exceedingly clear what direction the inertia of the industry is pointed. We continue to get critical feedback on the ultimate vision of a sustainable, scalable autonomous trucking solution.
Walter Grigg, Director of Product Strategy, Torc Robotics
We want to create a safer solution that will ultimately bring value to freight networks, to carriers, and to the end customer, the shippers. We believe that to do that it’s absolutely imperative that you collaborate with partners. So that means partnerships with OEMs like Daimler, it means partnerships with carriers as well to make sure we’re developing the right product and that it can integrate into the freight ecosystem.
With over 18 years of experience, King’s leadership will help propel Torc’s product development efforts
Torc Robotics, an independent subsidiary of Daimler Truck AG, has brought C.J. King on board as Chief Engineering Officer. King, who was previously Vice President of Software Engineering at HERE Technologies, brings more than 18 years of engineering, software, hardware, and autonomous expertise to the company. His leadership will drive the unification of all Torc’s engineering efforts to align with the company’s roadmap and key milestones. King’s experience on a global scale will support Torc’s Engineering team in its preparations for the commercial launch of Torc’s autonomous truck solution.
“Further strengthening our executive leadership team, C.J. is a critical hire on Torc’s path toward the commercialization of autonomous trucks for long-haul applications in the U.S.,” commented Peter Vaughan Schmidt, Torc Robotics’ CEO. “C.J. is a seasoned leader with the skillset and experience to propel Torc’s engineering efforts and vision forward, and we are thrilled for him to begin his work alongside the team.”
King has extensive expertise in product development, managing global, diverse teams, technology optimizations and new-system implementations as a result of his previous roles at HERE Technologies and as a Senior Software Development Manager at Amazon, where he led the Native Cloud Re-Architecture Engineering team. King also spent time at Ford Motor Company, where he oversaw their product development team for virtual driver development and at Toyota Motor Corporation, functioning as chief architect for next -generation multimedia systems and driving rapid integration of the latest consumer technology into automotive.
“From the start of discussions with the Torc team, it was clear that each and every team member was driven to truly transform the trucking industry,” commented King. “I look forward to collaborating and growing with this top-notch team as we continue to further develop Torc’s autonomous technology and products.”
ABOUT TORC ROBOTICS
Torc Robotics, headquartered in Blacksburg, Virginia, is an independent subsidiary of Daimler Truck AG, a global leader and pioneer in trucking. Founded in 2005 at the birth of the self-driving vehicle revolution, Torc has 17 years of experience in pioneering safety-critical, self-driving applications. Torc offers a complete self-driving vehicle software and integration solution and is currently focusing on commercializing autonomous trucks for long-haul applications in the U.S. Torc operates test facilities in Albuquerque, New Mexico, and engineering offices in Austin, Texas, and Stuttgart, Germany. Torc’s mission is saving lives with autonomous technology, which incorporates reducing highway deaths, enabling critical supplies – including medicines and foods – to reach every community in a timely manner, and helping the transportation industry increase fuel economy, uptime, and capacity.
I look forward to collaborating and growing with this top-notch team as we continue to further develop Torc’s autonomous technology and products.
The rise of artificial intelligence has been brewing for decades. In the past year alone, we’ve seen incredible developments in several forms of AI. From language models to personal assistants, this new technology has the potential to transform countless industries – and in some companies, it already has.
In the world of autonomous vehicles and self-driving semi-truck companies, Torc uses artificial intelligence every day as a tool for those self-driving semi-trucks, and to make some of our internal processes more efficient. AI is a part of our autonomous driving systems, but there’s a ton of misleading information out there about how it all works. Does artificial intelligence make all the same decisions that a human driver would make? What companies make the AI for self-driving cars and trucks? With the help of Torc’s Director of Engineering in Product Development, Justin Brown, we’re answering all these questions and more in this self-driving AI deep dive.
How do self-driving vehicles use AI?
Autonomous trucks collect an incredible amount of data while they are on the road due to the multitude of sensors used to localize and understand the environment around the vehicle.
Some of this data is fed into a machine learning pipeline, which is both a subset of artificial intelligence and a broad term used to refer to automated data processing.
Torc combines AI and traditional approaches to data processing to ensure it is balanced and traceable. On the road data processing enables the software in a self-driving 18-wheeler to take in data from its sensor suite and automatically classify it. Artificial Intelligence shines particularly in vision-based classification, helping the system define signs or objects made for human vision. It’s what allows our trucks to “see” a traffic light turning yellow, process that change, and decide to slow down.
At their core, self-driving semi-trucks are decision-making machines. Artificial intelligence helps provide additional information to make those decisions.
Think about the way that you learned to drive. There’s a good chance you made some mistakes that taught you a ton about putting the pedal to the metal. There’s also a good chance that you learned a lot about why being a predictable driver is such an important contender for safety – and you might’ve learned that human drivers aren’t always predictable.
Artificial intelligence and machine learning allow self-driving software systems to learn about the environment just like people do. Subsets of artificial intelligence, like the deep learning algorithms used in autonomous driving technology, run data through several layers of neural network systems (computer systems modeled after the human brain and nervous system – complete with artificial neurons) in order for the overall system to “learn by example”. The system may be trained on thousands of types of traffic lights, for instance, so the autonomous driving system can recognize one on the road.
Machine Learning and Responsible Use
While machine learning is certainly an important tool in our toolbox, it’s not the only approach we use for development. Our autonomous driving system uses diverse technologies, each selected for the right use case. Together, traditional code and artificial intelligence come together to recognize patterns, predict the movement of traffic and influence driving behaviors.
We also uphold rigorous standards of ethics and safety when it comes to machine learning. It is important to ensure our data collection processes are explainable and transparent. We work alongside government officials and regulators to create guidelines around concepts like data bias, sustainability, and other key factors. At Torc, we carry out careful consideration of issues like fairness, accountability, transparency, and privacy, in each stage of our development. As the technology continues to advance, we’ll work alongside our colleagues, policymakers, and researchers to create mindful processes around autonomous driving systems.
What kind of AI do self-driving vehicles use?
With the rise of chatbots, language models, and even neural networks that can create images, AI has become a vast and sprawling form of technology. However, there are many different types that can be used depending on use case. Currently, computer science defines AI in four types: reactive, limited memory, theory of mind, and “self-aware”.
Reactive AI is the most basic form of AI, wherein a machine is programmed with a specific output based on the given input. Most of us encounter reactive AI in things like recommended shopping algorithms, streaming service recommendations, and spam filters.
Theory of mind AI, or AI, is just coming to fruition; this type of AI interacts with the emotions and thoughts of people. Machines equipped with theory of mind AI will be able to gauge a person’s facial expression and adjust behavior based on that calculation.
Lastly, limited memory AI is the most common form of AI used today and, therefore, the most established – especially when it comes to self-driving vehicles and autonomous driving technology. It uses both historical and observational data alongside pre-programmed information to make predictions about the world around it.
What’s the difference between other forms of AI and ADS AI?
Limited memory AI is used in autonomous trucks, sometimes referred to as AV trucks, and other forms of self-driving vehicle technology for precisely the same reason as those chatbots. Limited memory AI allows a system to make decisions on its own, but within designated parameters.
In an autonomous 18-wheeler, this would be most apparent in things like road obstacles. Say that an automated semi-truck is driving along the interstate in Arizona. As the truck drives on, it detects a traffic cone knocked over in the lane ahead. The vehicle perceives the item and, via those pre-programmed parameters, calculates that this is an object that has the ability to move, but likely will not. Those pre-programmed parameters also inform the truck that it’s not necessarily a dangerous object, but it’s best to avoid all potential obstacles where possible.
The autonomous driving system for the semi-truck is using this prior information to “remember” that the cone can move. It can also be a signal to highway users that there’s reason for caution surrounding the cone. Via these deductions, it uses behavioral parameters to determine the best course of action. In this case, it’s likely moving out of the lane until the truck is clear of the obstacle.
Like any other form of AI, the artificial intelligence used by autonomous 18-wheelers is rife with myths and misinformation. “There’s a common misconception that the vehicle’s processing, and its AI systems, happens off the vehicle,” says Justin. “But navigation, perceiving what objects are and how fast they’re going – all that happens on the vehicle, so it doesn’t require an internet connection or anything like that.”
As a self-driving truck company, Torc takes pride in the safety of our technology and processes. Like all of our sensors and software components, we utilize artificial intelligence with the safety and security of pedestrians, drivers, and other highway users in mind.
“While AI is involved in the whole decision-making process of driving one of our trucks, it’s not the sole element,” Justin answered. “There are many systems ‘driving’, there are several sensors defining what its surroundings look like, and a ton of other processes happening.”
Justin Chong, Torc’s Director of Engineering in Product Development
How is AI trained in an automated semi-truck vs. other forms of AI?
Those language learning models that have been in the headlines have one key aspect to their education: it’s human-enforced. Every time a human engages with a language learning model (and sometimes sophisticated chatbots), that human assists in teaching the model how to behave. While this is an oversimplification of how those kinds of models work (and there is some supervised learning involved), it is a significant part of how these systems work at their core.
“The use cases for these autonomous semi-trucks is really specific and niche,” Brown answered when we asked him about these AI training differences. “But the systems aren’t sentient. AI doesn’t think for itself in the way that the movies make it sound – at least not yet. In the case of things like ChatGPT, those models heavily rely on replication, which is how you get a model that says things that are factually incorrect.”
Enter AI training for an automated semi-truck. In the early stages, data collection and selection is a huge part of how these vehicles are tested. Before a vehicle ever hits the road, its software and hardware is subject to a series of rigorous tests to ensure that all behaviors are performed as intended. Our engineers’ goal is to train on good data, ensuring that our systems have an in-depth body of knowledge with which to use. We can also utilize augmentation, inserting simulated objects into real data, to predict outcomes and test existing systems. Then, we measure the ADS performance in simulation to understand how we’re performing and make adjustments where necessary.
Once new software is deemed ready for on-road testing, we continue to collect data. When each test run is complete, the data collected from the run is analyzed by Torc’s team of forensic engineers.
Is AI driving a self-driving car or truck?
There are some important nuances involved in the way that driverless semi-trucks use these kinds of systems. Namely, its level of involvement.
“While AI is involved in the whole decision-making process of driving one of our trucks, it’s not the sole element,” Justin answered. “There are many systems ‘driving’, there are several sensors defining what its surroundings look like, and a ton of other processes happening.”
Artificial intelligence does help a vehicle recognize patterns and make decisions based on those patterns. However, in Torc’s autonomous driving system, there are some limitations to ensure that a neural network isn’t solely responsible for dynamic driving task decisions.
For instance, let’s say our autonomous freight truck’s route is impacted by road closures. While artificial intelligence may help the system recognize the traffic cones or other traffic control devices, other behaviors software parameters would be responsible for choosing the appropriate lane to move to, according to rules set by programmers. At times, traditional software rules may be more predictable, and thus, safer.
At Torc, our safety-first focus leads our development approach. Therefore, our AV trucks will always choose the safer option over the most convenient one.
Is AI the future?
Whether or not AI is the future for all industries and technologies is certainly up for debate. Artificial intelligence is an integral part of self-driving software, making it both a key piece of our technological present and future.
