Flying squad

The race is on to design a robot to be the roving eyes of Britain's armed forces. 

It is with a hint of disdain that Raglan Tribe nods across at the teams next to his company's table. "You see some of the other teams? They have all this equipment. We have just got this one vehicle," he says, pointing to the small battery-powered car sitting beside him.

Until Tribe and his colleagues at consultancy Mindsheet stripped it down and gave it a new electronic brain, it was a regular toy car. Now, it's a wheeled robot that is meant to find snipers hiding in alleyways and buildings. But Mindsheet was flanked by two teams that are not taking any chances in the UK Ministry of Defence (MoD) Grand Challenge final in the summer: they have one-time nuclear-waste and bomb-disposal robots that are meant to work alongside purpose-made aircraft and off-the-shelf gliders.

Eye on the prize

Tribe says his team had found soldiers who fought in conflicts such as Afghanistan to discover what they needed. Soldiers are pretty consistent in what they want: something light, easy to assemble and reliable. But, in the Grand Challenge, almost anything goes as the aim of most of the 11 teams is not the trophy - specially designed by the MoD and cast from part of the airframe of an original Spitfire - but the research and development contracts that will result from any piece of technology that piques the interest of defence users. The Grand Challenge is not so much a competition as a showcase for technology. And some teams want to make sure they have all their bases covered.

Steve Fernandes of Selex Galileo, which is part-funding the Stellar team, says they need to use both ground and air vehicles "to cover the range of threats. A ground-based system has limitations, as does a purely air-based system".

The Stellar team's entry will use a land robot built on the chassis of a bomb-disposal vehicle that will work with not one but two different unmanned aerial vehicles (UAVs).

"We have got our eyes on what comes after the competition and designed our whole architecture around that. The system has got a lot more built-in functionality that would be used in more representative scenarios," Fernandes adds. "What we have been doing is engaging the military customer to look at the scenarios and how the system could be deployed. We have tried to look across all the lines of development. We have tried to look at logistics and how the system fits in with other military equipment. And, most importantly, how it would link into the large systems currently deployed, such as Bowman."

But the link into the military networks has not escaped Mindsheet, as some companies involved with the Grand Challenge also want to see what small robots can do. Mindsheet and one other team took up an offer from MBDA to have its car hook into the defence-contractor's network. "We are using their ground station for mission planning and assembly of the data. We think it is a win-win arrangement, especially if we are to commercialise this work," says Tribe.

Mohan Ahad of MBDA says the company is using the competition to help develop software that can handle the data from autonomous or semi-autonomous robot vehicles. "This system is in development. We are helping the teams and they are helping us. The knotty problems are the integration issues: communications and working with the different protocols," he says, adding that software needs to do a lot of pre-processing on behalf of soldiers: "When you get a library of images, how do you go through them and determine what is important?"

Many of the teams have adapted off-the-shelf hardware. Some, like Mindsheet, are using adapted toys. Model helicopters are particularly popular, although their petrol-driven engines are noisier and will attract more attention from a marksman than the custom-designed battery-powered aircraft that were on show. Teams went with the readymade hardware because time was tight - the competition did not launch officially until spring last year - but also because a lot of the focus is on sensors and getting the vehicles to work autonomously. How much time vehicles can keep running is a problem - many of them will run for no more than a couple of hours on a full charge - but teams believe they can work on that later.

Bill Bailey, a consultant to Selex Galileo and former head of intelligence in Afghanistan, explains: "They are just platforms. If someone comes
out with a better platform,we can use that. And they have to be cheap because they will need to be replaced."

What the MoD wants to turn up are novel ways to watch for threats and how robots can work better with human operators.

Bailey says: "We just don't have enough assets to look after the tactical commander. If we can make this work, it will be revolutionary. All of a sudden, that young section commander can have something telling him that there is something there."

For the Silicon Valley team, giving the soldiers information will call for artificial intelligence. Professor Atta Badii of the University of Reading says: "Decision resolution is the biggest challenge: how does the escalation happen?" They are more difficult questions to answer than they seem. When the robot finds something, how does it tell the operator? And how does the robot know what might be a guerilla marksman taking aim out of a window rather than a civilian just taking in the view?


The approach that the university is taking with the software, which will go into the various robots that Silicon Valley is building, is to use aspects of artificial-intelligence research. The software takes the inputs from cameras and builds the processed image into a 'world view'. For example, if a moving object goes behind an obstruction, the robot expects it to reappear again at the other side. If it doesn't the robot may think something is up and keep watching or defer to an operator.

"It begins to think that it has got it all wrong, or that something is funny, and it defers to the human," Badii explains.

Like Stellar, the Silicon Valley team has decided to use an array of robots. The biggest one is the size of a quad bike and comes from Moonbuggy, a company that sells robots for monitoring radiation contamination where it is too dangerous to send in people.

A second robot, made by the same company, will also be used in the competition by Silicon Valley, together with a model glider armed with cameras. The images from the robots will be fed back to goggles fitted with a micro-display.

Harry Bragg, an engineering student at the University of Reading, says the smaller land robot is "a second set of eyes to traverse more of the area".

Fernandes says the Stellar team is working on ways to process the images its robots gather automatically. "We are doing algorithms that do change detection." Like the Silicon Valley robots, they will have some understanding
of what is normal and what might be suspicious. "Looking at the urban environment, if a street is normally heavily populated at one time of the day and, suddenly, it becomes sparsely populated, it can respond to that."

Mindsheet's initial design will be semi-autonomous, relaying video using a boosted WiFi signal to a handheld computer. "The vehicle is a toy car but very durable and it can go over just about anything," Tribe claims. "It has a top speed of 30 miles per hour. You download a mission plan to it, tell it where to go and where to stop, and it feeds back pictures."

The vehicles have range sensors as well as cameras to help them avoid obstacles. "There might be six vehicles out there, so they have to be able to move automatically. But it is the soldiers who distinguish between threats. The system buzzes the soldier and tells them there is a human there. The soldier can then react.

"We are working on a follow-on generation to detect threats automatically. We are gradually building in perception," adds Tribe.

The acid test will be whether the systems can perform on the day. In August, the finalists will demonstrate their capabilities at Copehill Down, on Salisbury Plain, Wiltshire, a village specially built by the military for urban warfare training. The winner takes home a trophy made from the metal of a Spitfire aircraft but most will have their eye on what the MoD does afterwards: whether it will snap up some of the technology or look at other options. 

Recent articles

Info Message

Our sites use cookies to support some functionality, and to collect anonymous user data.

Learn more about IET cookies and how to control them