Military working to make its autonomous technology smarter

Keeping soldiers safe continues to be the main reason the military enlists unmanned vehicles into its ranks, especially for resupply missions.

The U.S. Army has been tinkering with ground robotics and automated technologies for decades, yet there are still no real systems in the military field that are fully autonomous.

Nevertheless, the Army wants to finish what it started, so it plans to accelerate its use of autonomous defense technologies.

For now, rather than fully autonomous systems, there are semi-automated solutions that require having a soldier on hand, whether it's to monitor the technology or interact with it.

Engineer Bernard Theisen of the U.S. Army CCDC Ground Vehicle Systems Center in Warren, Mich., says the U.S. military faces challenges similar to those of commercial developers when it comes to autonomous vehicles.

"The biggest challenge deals with perceiving the world and then processing the data," he said. "For example, most humans take their driver's test when they're 16 or 18 years old, which is like 16 to 18 years of learning how vehicles and driving rules work. Now, we're trying to program a robot to take in all that information and figure it out. What happens is you end up with these edge cases or corner cases that the robot doesn't know how to handle, resulting in system failure.

"This is a significant thing that humans can do," Theisen said. "When we're engaged in a situation we don't understand, we usually build our own solution."

Another challenge that the U.S. military faces deals with testing vehicles and getting them to successfully adapt to changing environments. Theisen said the military will conduct tests in snow and ice, but it must first let the robot know that it's in snow and ice mode.

Robots rely on algorithm planners developed by humans. But if they encounter a situation not covered by the algorithm, they won't know what to do. For example, Theisen said, a self-driving car doesn't know how to react to a person in a wheelchair trying to chase ducks off a road.

"Right now, the intelligence is just not there for robots to smartly select between planners," Theisen said.

The military helped jump-start today's commercial AV efforts, most notably through competitions in 2004, 2005 and 2007 sponsored by its r&d arm, the Defense Advanced Research Projects Agency, or DARPA.

One of the most memorable DARPA entries was a behemoth called TerraMax, a driverless ground vehicle designed by Oshkosh Trucks, now Oshkosh Defense.

Oshkosh Defense has sidelined its efforts around TerraMax technologies in favor of the Army's new autonomous initiative called Expedient Leader-Follower.

Expedient Leader-Follower is a program where convoys are assembled that consist of one vehicle with a driver followed by driverless vehicles. It's part of the larger Autonomous Resupply Program at the U.S. Army CCDC Ground Vehicle Systems Center.

Theisen, who manages the Expedient Leader-Follower program, says the primary purpose of autonomous technology in convoys is to reduce the number of people operating tactical vehicles and limit exposure time to a potential attack.

The Army plans to issue 30 "optionally manned" vehicles to Fort Polk, La., in September for testing, and 30 will go to Fort Sill, Okla., in January, he said.

"The vehicles that we are going to be issuing will have two robotic functions," Theisen said. "The first one is what we call the teleoperation, where the commander can remotely control the motion of the vehicle from a remote location. The second mode is leader-follower, where vehicles robotically follow the first vehicle, in which there will be nobody in those follower vehicles."

The U.S. Army CCDC Ground Vehicle Systems Center began developing its autonomous offerings before Theisen started working there 18 years ago.

As Theisen puts it: "We've been doing autonomy a lot longer than the Waymos and Teslas of the world."

He notes that some technologies that were developed by the military — such as GPS and radars — have been placed into the civilian sector but are now coming back to benefit the military once again.

Many sensors such as higher- end lidar or radar, and some navigation systems, have been too expensive for Army vehicles.

"Starting in the late '90s, early 2000s we saw the automotive market moving toward active safety sensor technologies," Theisen said. "We were able to start bringing some of the commercial sensors back into the tactical fleet, and it enabled us to use the lower-cost sensors to make robotics more affordable on tactical trucks."

As for whether full autonomy is feasible in the near future, Theisen says that while he can't speak for automakers, he knows the mobility future is complex.

"There's a lot of things that play into it like liability and the legality of everything like who's responsible if their autonomy fails, the consumer or [automaker]," he said. "There's also the costs of the system that's complex. I don't think there's a price point for the sensing computer needed that can be brought down low enough for the normal consumer right now."