Institute For The Future

Hybrid mongoose-robot system detects land mines

As most of us know, landmines are a serious threat to both soldiers in wartime and civilians in peacetime. (Farmers and construction workers in Europe still occasionally find landmines from World War II.) Finding and disabling them has traditionally been dangerous, time-consuming work. Engineers in Sri Lanka have developed a "human-animal-robot integrated system" to find anti-personnel landmines.

As Thrishantha Nanayakkara, Tharindu Dissanayake, Prasanna Mahipala, and K. A. Gayan Sanjaya report [PDF],

 

a mongoose was trained to sniff for landmines. It was attached to a semi-autonomous legged mobile robot. The robot could sense the direction of movement of the mongoose. The robot used this direction information along with commands sent by a remote human operator to modify its own semi-autonomous behaviors. The human operator gave overall commands as to which direction the robot should move. The robot took care of detailed tasks such as obstacle avoidance, monitoring the environment immediately in front of it, and guiding the mongoose. The mobile robot was a laboratory made fully embedded platform with simple sensors such as bumper switches and a sonar sensor. Experiments were carried out in typical environments where anti-personal landmines are buried in Sri Lanka.

 

Like social software, which combines what computers are good at (managing vast quantities of information) with what humans are good at (making judgement and providing context), the system is interesting because it takes a smart approach to building a system that combines several different forms of intelligence and physical capability. Rather than designing an expensive technology that mimics animal senses, it simply uses an animal; and rather than using complex software to make tricky decisions, the system keeps a human operator in the loop. As the designers explain,

 

The proposed system tries to

integrate distinct capabilities of three different systems to improve the effectiveness of

landmine detection in a cluttered environment. The mongoose is found to be a rodent with

extremely sensitive olfactory capabilities, dexterous navigation capabilities in a cluttered

environment, and small enough to burrow through rubble. The lightweight legged robot

(4kg) can move in a minefield without detonating landmines, carry a metal detector, and

interact with the mongoose and the human. The remote human operator can analyze the

behaviors of the animal-robot system and judge how best the system should move from a

remote location. Therefore, the system achieves a fundamental objective of humanitarian

landmine detection by improving the effectiveness and accelerating the detection process

through removing the human operator from the minefield. The design gave much emphasis

on reducing the need to have expensive sensors and sophisticated image processing systems

in order to make it as cost effective and reliable as possible. Therefore, there were only a

single sonar proximity sensor and two bumper switches attached to the front of the robot.

 

We see a lot of promise in biotechnology, biomimicry, and other high-tech tools that draw on nature for inspiration; but I suspect that the ability to design chimeras like these, and to build systems that combine the very different skills of humans, animals, and technologies, may be just as important.

[via New Scientist]