- DARPA confirmed its RACER autonomy program has completed final tests and is ready for transition to U.S. military use after demonstrations with Army units in 2025.
- The RACER software stack enables ground vehicles to operate autonomously without GPS and is now available for military and commercial adoption.
DARPA, the Pentagon’s research and technology arm, confirmed on January 14, 2026, that its Robotic Autonomy in Complex Environments with Resiliency (RACER) program has completed final operational tests and is ready for transition to U.S. military units and commercial users.
The announcement follows a series of Army and Marine Corps demonstrations that showed RACER-equipped vehicles operating autonomously in complex, off-road terrain without GPS or pre-mapped routes and at mission-relevant speeds. DARPA said the results fulfill the original promise of its 2004–2005 Grand Challenge, which sought to accelerate the development of autonomous ground systems for military use.
RACER is not a single vehicle program but a reusable autonomy software stack consisting of algorithms, datasets, and neural network models that can be installed on multiple types of ground vehicles. DARPA said the system can turn sensor-equipped platforms into autonomous vehicles capable of navigating contested and degraded environments without human control.
In October 2025, DARPA partnered with the U.S. Army’s III Armored Corps and the 36th Engineer Brigade during a combat breaching demonstration under the Machine Assisted Rugged Soldier program. The Army used the RACER Heavy Platform, built by Carnegie Robotics on a Textron M-5 chassis, and paired it with an M58 MICLIC rocket-projected mine-clearing line charge to autonomously clear a lane through a minefield.
“Our focus on real-world performance will translate directly into tangible benefits for military users,” said Stuart Young, RACER program manager at DARPA. “The combat breaching demonstration proved not just what technology can do, but how it can change the future of force protection.”
In November 2025, soldiers from the 11th Armored Cavalry Regiment employed RACER-equipped vehicles as an opposition force during a live force-on-force exercise at the National Training Center in Fort Irwin, California. The unit used RACER Fleet Vehicles based on the Polaris RAZR platform to conduct autonomous long-range reconnaissance with integrated intelligence, surveillance, and reconnaissance payloads.
“By decreasing reliance on GPS and pre-programmed paths, RACER ensures warfighters can deploy autonomous assets in any environment, even when operating off the grid,” Young said. “Instead of human scouts going 12 or 15 kilometers into enemy territory, that dangerous work can be handled by a robot while humans are safe.”
Sergeant First Class Gavin Ros of the 11th Armored Cavalry Regiment said the system met operational needs during the exercise. “I think it’s a great system; [RACER is] working very well for what we need it to,” he said.
DARPA said one of RACER’s main achievements is its perception architecture, which allows autonomous vehicles to predict terrain and adjust behavior in uncertain environments. Unlike earlier systems that required weeks of retraining, the RACER system can adapt to new terrain in about one day, according to DARPA, allowing rapid redeployment to unfamiliar environments.
“We make predictions about the world based on the evidence that we’ve seen and our prior information and can adjust even in ambiguous situations,” Young said. “So part of that adaptation is learning the new environment.”
DARPA validated this perception system during its final RACER experiment at the Fort Irwin National Training Center, completing eight major experiments conducted during the program’s lifespan.
With military testing complete, DARPA said the RACER autonomy stack is now ready for transition to the U.S. Department of War and to private industry. The agency noted that multiple companies have already emerged from RACER-funded research, including Field AI and Overland AI, which are developing commercial off-road autonomy systems for sectors such as agriculture, mining, construction, and transportation.
DARPA said the dual-use nature of the technology has attracted interest from private investors, as the same autonomy software used in military vehicles can be applied to commercial platforms with minimal modification. The agency described the end of the RACER program as the beginning of broader adoption rather than the conclusion of its impact.