May 20, 2010: After years of research, and four competitions, the U.S. Army is putting together its long sought ANS (Autonomous Navigation System). Over the next five years (or so, as these things go), a combat ready ANS will be built. This will equip cargo and combat vehicles with a standard set of sensors and computers that enable them to deal with all the hassles of moving cross country, or on crowded roads. There's always a human in the command loop, ready to shut down the ANS control, or, more frequently, to tell the vehicle where to go (either along a road or cross country). But the ANS is capable of navigating obstacles on the road or cross country on its own. On the road, the ANS vehicle would usually be in a convoy, and following another ANS vehicle, or the command vehicle, which would be under human control. Thus the ANS vehicle would speed up or slow down according to the vehicle in front of it, or because of any obstacle (a person or animal) suddenly darting in front. Vehicles on the road could also be ordered off the road, in the event of an ambush or some other emergency. If the command vehicle was destroyed, a human controller back at headquarters, or overhead in an aircraft, could take over control of the ANS vehicles.

The most ambitious robotic vehicle is the ARV-A-L (XM1219 Armed Robotic Vehicle-Assault-Light, or “Arval”). This 2.3 ton, six wheeled armored vehicle is armed with an 25/30 or 40mm autocannon, and four guided missiles (TOW, or something smaller). Arval would always have a human controller, and a lot more sensors (including a thermal imager). Here, ANS would serve mainly to play the role of a vehicle driver, while the human controller would be the vehicle commander and gunner. Because of the larger number of sensors, there might be a human gunner, in addition to the human commander. Arval would be in touch with combat troops it is operating with, although the current plan is to have the controller back at a headquarters, or even back in the United States (using satellite communications). Arval would be used for providing firepower, as well as patrolling and covering flanks. These last two missions are dangerous, and the troops don’t mind having robots replace them there. The key element here is ANS, which enables the vehicle to scan for, and avoid, or negotiate (slowing down to roll over a log or small ditch) potential obstacles.

There is also a tactical cargo vehicle, called a MULE, that takes supplies cross country, especially in areas covered by enemy fire. The army also plans to equip existing combat vehicles (M-1 tank, M-2 and Stryker infantry vehicles) with ANS, so they can be sent into very dangerous situations without their human crews. Existing trucks would also be equipped with ANS, to reduce manpower needs, and potential casualties, for dangerous convoy missions.

ANS is the key element, and why is the army so confident that they have ANS ready for prime time. Much of the credit goes to four competitions the Department of Defense held for commercial firms, to demonstrate their ANS type systems. The winners were awarded millions of dollars in prizes, and a shot at the contracts to develop and build the ANS family of vehicle.

Last year, the army's decades long effort to develop a practical autonomous UGV (Unmanned Ground Vehicle) appeared to have succeeded. That was when the fourth Grand Challenge competition saw two T2 vehicles, equipped with sensors and control equipment, successfully pass realistic tests. One of the test subjects, controlled from a Stryker wheeled armored vehicle, successfully approached a village (equipped with mannequins set up as pedestrians along the streets), did a perimeter sweep at speeds of up to fifty kilometers an hour, then patrolled the streets, avoiding the pedestrians, and finally departed the area. The sensor systems uses a combination of ladar (laser radar), digital cameras and heat sensors, to provide the software with sufficient data to enable the onboard computers to identify and avoid obstacles. The key element here was the software, which, in turn, benefited from five years of competitive events that delivered software advances faster than expected.

For several decades, the U.S. Department of Defense has been trying to build a robotic vehicle. But in early 2004, the Department of Defense decided to try something different, and give enterprising civilian organizations a chance to show what they could do. DARPA (Defense Advanced Research Projects Agency) held the DARPA Grand Challenge. Put simply, the first robotic vehicle (moving completely under software control, with no human intervention) that could complete a 240 kilometer course, would get a million dollars for its designers. No one even came close. But a second Challenge, held in late 2005, yielded several finishers, and the first one picked up the million dollar prize for navigating a 212 kilometers cross country course in just under seven hours. All vehicles operated under software control, as true robots. The third "Challenge" race was held in late 2007, and had a two million dollar prize for the first vehicle to complete a 60 kilometer course through an urban environment (an abandoned air force base) in under six hours. The fourth Challenge, held last year, was even more successful.

 While much progress has been made, the basic problem is, and always has been, that there are a lot more obstacles for a robotic land vehicles to deal with on its own. At sea, and in the air, it's a much different, and much simpler, situation. Over a century ago, naval torpedoes were built that could make sufficient adjustments, while under way, to reach their intended target. Guided missiles came along half a century ago and achieved the same thing in the air.

The DARPA Challenge contests convinced developers of robotic vehicles that they have to give their creations a large amount of basic knowledge of obstacles, and how to deal with them, to consistently succeed. Until now, robotic vehicles depended on TV cameras (linked to computers that could detect traversable paths), laser rangefinders and the like to "learn on the go." But for a robotic vehicle to succeed, it needs some basic knowledge of the world. There is sufficient cheap computing power available to provide that, and robotic vehicles make use of this approach. This is also creating the kind of "knowledgeable robots" that have for so long been popular in Science Fiction literature.

One of the goals of all this is a robotic "infantry mule" (a low slung vehicle that brings supplies to infantry deep in a combat zone) with a speech recognition and voice synthesizer module so that, when the troops wondered aloud why the mule took so long to get the stuff to them, the vehicle could respond, "there was a lot of mud down the hill today and I had to go around it." Equipping a robotic vehicle with sensors that can detect water, mud, and the depth of both, is the sort of thing a successful "mule" will require to survive on a battlefield. Being able to respond to audible commands is another feature the troops have already requested for such a vehicle. So the effort is not just to build a robotic vehicle, but a robot in the classic sense. That's how much computing power is required to enable a machine to go for a cross country trip over unfamiliar terrain, and succeed.

Based on the performance of Challenge vehicles, the army is pretty sure they have the on-road system working. But the cross country stuff still needs work. Cross country navigation is just a more complex version of on road operations.

Ultimately, the military wants an ANS that enables robotic trucks to safely move supplies over roads, or cross country, with only a few troops supervising a dozen or more robotic vehicles. This means you need fewer troops in the combat zone, and fewer troops will become casualties.

The DARPA Challenge races have been a bonanza in terms of advancing the state of the art for robotic vehicles. For less than $10 million in prize money and expenses, the Department of Defense has created new technology that would have otherwise cost more than $100 million, and taken a lot longer to perfect.

The T2 vehicle used in the recent test, also benefitted from the DARPA completion. The T2 vehicle weighs 620 kilograms (1350 pounds) and has six, independently controlled, wheels. It is very agile, and has sufficient carrying capacity to handle the sensors and computers. A scaled up T2, with enough armor to make it bullet proof and able to survive nearby explosions, would enable it to survive some ambushes or light resistance. This is Arval. A Stryker platoon (four Strykers) could be accompanied by two or more Arvals for scouting, especially in areas where there is likely to be strong resistance. Such Arvals would also be equipped with speakers, enabling an interpreter in one of the Strykers to question locals.