RACER’s finish line

The promise of DARPA's Grand Challenge is being fulfilled 20 years later.

After years of aggressive testing and pushing the envelope with U.S. Army and Marine Corps partners, the Robotic Autonomy in Complex Environments with Resiliency (RACER) program approaches its conclusion. But the impact of RACER will reverberate far beyond the program's official end date, leaving a legacy of robust autonomous capabilities ready to transform military operations and inspire a new wave of private sector investment.

RACER was never about building a single, specialized vehicle. Instead, DARPA aimed to develop an autonomy "stack" - a collection of algorithms, datasets, and neural network models - that could be deployed on any ground vehicle. Fast forward from when the program first began in 2021, users can now apply the RACER stack to any vehicle (equipped with appropriate sensors), turning it into an autonomous machine capable of operating in challenging off-road environments, independent of GPS or pre-mapped routes, and at mission-relevant speeds.

Choose Your Capability

"RACER isn't just about replicating existing military capabilities." said Stuart Young, DARPA RACER program manager, "It's about fundamentally reimagining how missions are executed."

In a series of final tests, demonstrations, and experiments this Fall, RACER vehicles demonstrated the ability to navigate complex terrain without human intervention, freeing up soldiers for other critical tasks.

In October 2025, DARPA partnered with the U.S. Army's III Armored Corps' 36th Engineer Brigade at their combat breaching demonstration as part of the Machine Assisted Rugged Soldier program. Using the RACER Heavy Platform vehicle, the robotic platform created by Carnegie Robotics LLC based on a Textron M-5 chassis, the Army paired it with a M58 MICLIC - a rocket-projected mine clearing line charge used to clear direct passages for combat personnel through minefields.

"Our focus on real-world performance will translate directly into tangible benefits for military users," said Young. "The combat breaching demonstration proved not just what technology can do, but how it can change the future of force protection."

In a demonstration, the Army pairs RACER with a M58 MICLIC, a rocket-projected mine clearing line charge, to show how the autonomous vehicle can clear direct passages for combat personnel through minefields. | 0:54

No Babysitter Needed

In November 2025, soldiers from the reconnaissance squadron in the 11th Armored Cavalry Regiment (ACR) used RACER technology as part of the opposition force in a live force-on-force exercise at the National Training Center. The 11th ACR Soldiers tasked RACER Fleet Vehicles (RFVs), the Polaris RAZR based platform, with an integrated intelligence, surveillance, and reconnaissance (ISR) payload to conduct autonomous long-range reconnaissance, a capability they've never had before.

"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," explained Young. "Instead of human scouts going 12 or 15 km into enemy territory, that dangerous work can be handled by a robot while humans are safe, and the risk is minimized."

"I think it's a great system; [RACER is] working very well for what we need it to," said Sergeant First Class Gavin Ros. "I'm very interested to see in the direction that it's going to go with the advancements in the software and the system in general."

Soldiers use RACER in a live force-on-force experiment. | 1:20

Adapting Faster Than Ever

The most significant accomplishment on the RACER program is its perception architecture.

Imagine you're driving down a country road...

The asphalt stretches out before you, dipping over a gentle hill. You don't slam on the brakes at the crest, even though you can't see what's on the other side. Why? Because you predict the road will continue. You have a priori insight - a belief based on experience - that roads don't usually end abruptly. This is the essence of RACER's advanced perception architecture.

But what if something feels off? Imagine that same country road, but now you see a car parked awkwardly on the shoulder and a cluster of orange cones ahead. Your internal "uncertainty" alarm bells start ringing. You ease off the gas, paying closer attention. Are there construction workers ahead? An accident? You adjust your behavior, becoming more cautious and reactive due to a combination of missing information and a feeling that something isn't quite right.

"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," explained Young. "So part of that adaptation is learning the new environment."

Earlier autonomous systems were slow to adapt to a new environment, requiring weeks of retraining. With RACER, the turnaround is dramatically faster.

According to Young, what would normally take weeks to retrain a new model can now be done in a day.

"That kind of agility is invaluable for warfighters who need to deploy robotic assets rapidly to unfamiliar terrains," said Young. "In situations where speed and adaptability are paramount, RACER empowers them to swiftly adapt the autonomous system to specific, real-world conditions."

RACER's architecture enables autonomous systems to reason and react to the world much more like a human driver. It's not about just reacting to what's directly in front of the vehicle; it's about anticipating what's likely to happen next, even in the face of incomplete or ambiguous information. This means higher speeds, greater safety, and the ability to operate in environments too complex and unpredictable for earlier autonomous systems.

The DARPA team recently proved this perception architecture at its final experiment at the Fort Irwin National Training Center in California.

DARPA advances scientific goals in perception at its eighth and final RACER experiment. | 1:13

Ready for Transition: An Opportunity for Private Equity

RACER's impact extends beyond the battlefield, creating a fertile ground for private investment. By developing dual-use technology, RACER has sparked the interest of both the Department of War and the private sector. This has allowed others to invest in similar technology and to help bridge the gap that is so often heard about.

Multiple companies have grown out of the RACER program, helping to build a market for off-road ground vehicle autonomy. These include Field AI, which spun out of DARPA-funded research at NASA's Jet Propulsion Laboratory and Overland AI, from research at the University of Washington Robot Learning Laboratory.

For private equity firms, RACER presents a unique opportunity to capitalize on proven and adaptable technology. The core autonomy stack is readily transferable to commercial applications in industries like agriculture, construction, mining, and transportation.

"Now that the RACER program is ending, there is a lot of commercial opportunity for private equity," said Young. "It's time for both military users and private investors to recognize the transformative potential of RACER and embrace a future where autonomous systems are not just a possibility, but a reliable and integral part of our world."

Take a Ridealong with RACER

In this 360-degree video, experience what it's like to ride along the RACER Heavy Platform during the mine clearing demonstration. Best experienced with 4K quality and a VR headset. | 3:36

###

Media with inquiries should .