TRANSPORTATION & NATIONAL SECURITY

Sandia Conducts Next-Level Test for Secure Transportation Vehicle

Mobile Guardian Transporter crash test provides critical data.

ALBUQUERQUE, N.M.—With rockets propelling it down the sled track at Sandia National Laboratories, a semitrailer loaded with mock nuclear weapons slammed into a barrier. It took mere moments to complete the second and final full-scale crash test of the Mobile Guardian Transporter, a next-generation system that will carry nuclear weapons and other sensitive materials for the Department of Energy’s Office of Secure Transportation.

The tests are designed to demonstrate that, if a trailer were ever involved in an accident on a public road, the cargo inside would remain secure and pose no danger to nearby communities, a key tenet of the Office of Secure Transportation’s mission and vision.

“This was our last opportunity to understand how the trailer performs in a crash,” said Jason Berger, the program’s crash test lead for the second test asset. “The results will help qualify the design, a critical step before production can begin.”

Sandia conducted a side-impact crash that evaluated the first Mobile Guardian Transporter test asset in 2020. The second test completes the full-scale crash series and gives engineers a more complete picture of how the trailer performs in severe accidents.

“The second prototype crash test is a critical step in showing that the trailer and its cargo do not pose a hazard to the public,” Berger said.

“We are extremely proud of the commitment and dedication of teams across Sandia and our external partners, who applied their knowledge to make this a successful test,” said Kelly Neely, the senior manager overseeing the Mobile Guardian Transporter program. “It’s taken focus, determination, and technical expertise to get us to this point.”

Test planning and execution

While the test itself lasted only a few moments, planning and preparation took about a year and a half. For a test of this scope, that’s not very long.

“This was a very heavily instrumented test and the overall scope of it was very large,” said James Dykes, the test director. “These kinds of large-scale, high-consequence tests don’t come along very often because of the complexity. It was the largest data collection effort in the history of Sandia’s rocket sled track facility.”

A test with 100 channels of data collection and a few cameras would already be considered complex. In this test, the trailer was equipped with nearly 500 data channels for acceleration, strain, force, and temperature, plus about three dozen cameras, when rockets propelled it down Sandia’s sled track in the fall of 2025.

Test coordination

As part of the planning process, the team created redundant pathways and backup channels to ensure they could capture the most critical data if some equipment failed.

“With this test, we’ve gone beyond the bounds of what is understood commercially and inside Sandia for data collection and acquisition,” Berger said. “To accomplish this, Sandia’s sled track test team stood up a temporary multi-acre facility with a control center, data collection trailers, and console trailers near the sled track. Working at a remote, undeveloped site introduced many challenges. Strong monsoon storms caused flooding at the sled track multiple times, but the teams worked through these challenges to ensure the test occurred on schedule.”

Impact on weapons programs

Several nuclear weapons modernization and stockpile programs provided hardware for the test, including Los Alamos and Lawrence Livermore national laboratories. These systems represent different types of nuclear weapons that must be transported.

“Nuclear deterrence programs need to assess safe and secure transportation for each weapon type,” said Tara Olivier, a Sandia senior manager working in nuclear deterrence. “Gathering the environmental data from the crash will help qualify those systems on the Mobile Guardian Transporter.”

With so many partners, a large task in test planning was getting everyone on the same page.

“It’s a huge effort to coordinate all of the teams, and then to ensure we’re doing the right test and collecting the right data,” Berger said.

As part of the test, the trailer, restraints, and the shipping containers for the weapon systems were pushed to their limits. Capturing the right data was essential for understanding how this hardware performed and for supporting future design qualification.

Validating the models

With the test complete, the team is now focused on analyzing the data.

“We met all our testing objectives, including the speed at which the trailer crashed. We’re where we wanted to be with data acquisition and collection,” Dykes said.

The Mobile Guardian Transporter team will continue working closely with modeling and simulation teams to compare the test results with pretest predictions and refine their computer models.

“Using the crash test data, we’ll build a modeling and simulation tool that will allow us to analyze many different crash environments,” Berger said. “The modeling and simulation tool will be our enduring tool to assess trailer performance, assess safety of our weapons systems during transport, and assess nuclear safety of the trailer.”

Key partnerships

Strong partnerships across the nation’s nuclear security enterprise were essential to executing a successful test.

“Executing this crash test is a shining example of Sandia integration and what we can do,” Berger said. “Large-scale systems-of-systems tests involve many stakeholders and, specific to the crash test, it was critical that the Office of Secure Transportation, NNSA and Sandia, Los Alamos and Lawrence Livermore national labs were all in lockstep for funding, delivery of test hardware on schedule, and development of a complex technical basis and data collection design.”

At Sandia, the design agency for Office of Secure Transportation’s Mobile Guardian Transporter and the lead systems integrator for nuclear weapons programs, about 200 employees worked on the test.

“Completing the crash test for the Mobile Guardian Transporter is a significant accomplishment, thanks to the dedication and commitment of many Sandians and our exceptional partners,” Labs Director Laura McGill said. “Safe and secure transport is a key element of maintaining a credible deterrent.”

The Kansas City National Security Campus’s New Mexico Operations location is the production agency for the Mobile Guardian Transporter. The crash test data will help inform final design decisions and support future production of the new transporter fleet.

Sandia National Laboratories is a multi-mission laboratory operated by National Technology and Engineering Solutions of Sandia LLC, a wholly owned subsidiary of Honeywell International Inc., for the U.S. Department of Energy’s National Nuclear Security Administration. Sandia Labs has major research and development responsibilities in nuclear deterrence, global security, defense, energy technologies, and economic competitiveness, with main facilities in Albuquerque, New Mexico, and Livermore, California.

This article originally appeared on the Sandia National Laboratories website.

 

 

Teaching Drones to Play Tag

Autonomous drones compete, demonstrate national security uses

ALBUQUERQUE, N.M.—The rules of tag are simple enough for a playground: Catch or be caught.

But when the players are autonomous drones, the game becomes a test of machine learning, split-second decision-making, and cooperative strategy.

Researchers at Sandia National Laboratories recently used reinforcement learning, a kind of machine learning, to teach drones how to play a strategic version of the game. The work could help advance algorithms for autonomous systems that need to pursue, evade, or coordinate in rapidly changing environments, including future systems designed to defend critical facilities from hostile drones or other national security uses.

The project is part of a larger effort called AutonomyNM that uses machine learning and artificial intelligence to push the boundaries of what is possible in autonomy. Unlike remote-controlled drones, autonomous drones use algorithms to decide how to respond to a scenario, avoid obstacles, and achieve a defined objective. Autonomy has the potential to enable more rapid responses and reduce human error in drone swarms.

The team’s work, including how the researchers trained the drones and compared their performance with other strategies, was recently published as a conference paper for the 2026 IEEE International Conference on Robotics and Automation.

“We have expertise in reinforcement learning algorithms,” said Spencer Jensen, Sandia computer scientist and lead researcher on the project. “Reinforcement learning is just beginning to be used in commercial robotics. The really nice thing about reinforcement learning is you can ignore a lot of extremely complex math—that’s probably slightly wrong anyway—and just get a best-effort algorithm that is going to be more flexible in rapidly changing scenarios.”

Reinforcement learning: Like training a puppy

In Sandia’s version of tag, two pursuer drones protected a safe “base” while two cooperating evader drones tried to reach it. The evaders were trained to work together to cause the pursuers to crash into each other, allowing the evaders to reach the base without being tagged—or, in this case, crashed into—by the pursuers, Jensen said.

The researchers used reinforcement learning to teach the evading drones how to cooperate. Reinforcement learning, like training a puppy to sit on command, uses virtual rewards to guide the algorithm toward the desired behavior.

“The challenge with reinforcement learning is you have to do a lot of reward shaping to get the behavior you want,” said Christian Llanes, a Sandia intern on the project and robotics doctoral student at the Georgia Institute of Technology. “Reward shaping is a twofold problem where you determine what behaviors you want to reward or penalize and how much reward or penalty you want to give.”

Llanes started working on the project in fall 2023 after completing a summer internship on a similar project. He used reinforcement learning to train the evading drones’ guidance module in computer simulations. The guidance module dictates a path for the drone’s control module to follow.

For the evading drones, reinforcement learning offered a way to develop more flexible behavior without programming every possible move.

“Reinforcement learning is a simulation-based guidance technique,” Jensen said. “We really like reinforcement learning because that behavior can be very hard to optimally program, but is something that reinforcement learning can just learn how to do optimally. It makes the complex simple.”

The pursuers were not trained and instead followed a more straightforward algorithm called proportional navigation, which simply seeks to intercept its target, Jensen said.

Going from a computer to the real world

Once the evading drones’ guidance module was fully trained, the team took the algorithm from simulation to the real world and tested it on small, inexpensive drones.

A major challenge was the difference between how an algorithm performs in a computer model and how it behaves on physical hardware.

“With reinforcement learning, one of the common problems is the simulation-to-reality gap,” Jensen said. “Because this is a simulation-based guidance method, it often doesn’t work very well in hardware because of all these unmodeled dynamics.”

The team adjusted for this by studying the small, inexpensive commercial off-the-shelf quadrotor drones more fully at the beginning of the project and better modeling them in the simulation, he said. However, some issues—such as how a draining battery affects rotor speed and how one drone can create wind that affects another—are hard to fully model. There also are many small communication delays in the real world that do not exist in simulations, Llanes added.

The team used inexpensive drones that are about 3.5 inches wide and weigh less than a chocolate bar because they can crash into each other or drop out of the sky without ill effects beyond an occasional inexpensive plastic piece snapping off, Jensen said. Repairs are much faster and easier than on larger drones, allowing the team to test improved algorithms rapidly, he added.

The drone lab used for testing has a state-of-the-art infrared motion-capture system, similar to those used in Hollywood movies, to track the position of the drones with high precision. The facility, located in the Center for Advanced Manufacturing and Innovation, or CAMINO, allows Bluetooth-enabled drones to be tested, streamlines internships, and facilitates research partnerships with universities and local businesses.

“The high bay in CAMINO allows us to bridge the gap between early-stage research and high-consequence hardware,” Jensen said. “We can do low-cost testing in this facility. A lot of the work we’re doing is trying to bridge the simulation-to-reality gap. Our goal is to work out some of the bugs on low-cost hardware before we move on to high-cost, high-consequence hardware.”

This research project and was funded by Sandia’s Laboratory Directed Research and Development program.

Sandia National Laboratories is a multi-mission laboratory operated by National Technology and Engineering Solutions of Sandia LLC, a wholly owned subsidiary of Honeywell International Inc., for the U.S. Department of Energy’s National Nuclear Security Administration. Sandia Labs has major research and development responsibilities in nuclear deterrence, global security, defense, energy technologies and economic competitiveness, with main facilities in Albuquerque, New Mexico, and Livermore, California.

This article originally appeared on the Sandia National Laboratories website.