Logistics: Challenging Solutions

Archives

May 8, 2022: For several decades the U.S. Department of Defense has been trying to build robotic military vehicles. Progress was slow and in 2004, the Department of Defense decided to try something different, and give enterprising civilian organizations a chance to show what they could do competing with defense contractors. Thus began the ongoing DARPA (Defense Advanced Research Projects Agency) Grand Challenge competitions. The goal was to develop safe and reliable systems that would allow supplies to be moved to the troops via vehicle convoys, without the need for lots of drivers. These competitions have led to vehicles reliable enough for troops use.

The last three Challenge competitions went underground and involved exploration and mapping of underground situations using walking robots as well as wheeled vehicles. This was all about robotic support for disaster situations where the first task is to determine what the situation is down there. The SubT (subterranean) competitions achieved a lot of progress in identifying problems with communication and mobility problems underground.

These competitions are open to anyone (commercial, academic or defense contractor) who has a vehicle capable of competing. The candidates pay their own expenses to develop entrants and get them to the Challenge site with a team of technicians/operators.

The first Grand Challenge competitions concentrated on determining who had made the most progress in developing hardware and software that enabled a robotic vehicle, moving completely under software control, with no human intervention. For the first competition the goal was to complete a 240-kilometer course. The first vehicle to complete the course would earn the winning team a million dollars and lots of good publicity for their capabilities. No one even came close, but the competitors were eager to modify their designs and try again. This led to a second Challenge, in 2005, which yielded several finishers, and the first one picked up the million-dollar prize for navigating a 212-kilometer cross country course in just under seven hours. All vehicles operated under software control, as true robots. The third Challenge was held in 2007, and had a two-million-dollar prize for the first vehicle to complete a 60-kilometer course through an urban environment in under six hours. A recently abandoned air force base was used. The fourth Challenge, held in 2009 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 vehicle 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 underway, to reach their intended target. Guided missiles came along after World War II 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. 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 managed to obtain an on-road system that worked. But the cross-country model needed more work. Cross country navigation is just a more complex version of on road operations. The SubT competition provided useful tech for military and non-military disaster relief operations.

One of the earlier competitions involved a Stryker wheeled armored vehicle, successfully approaching a village (equipped with mannequins set up as pedestrians along the streets), doing a perimeter sweep at speeds of up to fifty kilometers (31 miles) an hour, then patrolled the streets, avoiding the pedestrians, and finally departed the area. The sensor systems used 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.

Ultimately, the military wants systems that enable 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 events 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.