Autonomous systemsUnmanned systems emulate animals’ conditioned fear-response mechanism for self-preservation

Published 16 July 2012

When animals in the wild engage in eating or grazing, their eyes, ears, and sense of smell continuously monitor the environment for any sense of danger; researchers developed a similar conditioned fear-response mechanism for unmanned systems

When animals in the wild (think deer, zebra, buffalo, etc.) engage in eating or grazing, they do not turn off their fear-response instinct. As they go about eating, their eyes, ears, and sense of smell continuously monitor the environment for any sense of danger – and if they pick up a sign of danger, they immediately respond by fleeing, huddling closer together, and other conditioned responses. Researchers think that autonomous vehicles — in the air, on the ground, and at sea – would benefit from emulating nature in this regard.

Roke Manor Research Ltd, a Chemring Group company, has developed what it describes as the world’s first threat monitoring system for autonomous vehicles. The system emulates a mammal’s conditioned fear-response mechanism. The STARTLE system uses a combination of artificial neural network and diagnostic expert systems continually to monitor and assess potential threats.

The company says STARTLE provides enhanced situational awareness and early threat warning to both the autonomous vehicle and to its remote operator(s). Making use of existing hardware, STARTLE processes information from multiple on-board sensors, cueing systems to assess and confirm potential threats to the vehicle.

Mike Hook, principal consultant at Roke, said:

STARTLE reduces operator workload and improves vehicle efficiency on the ground by helping remote operators to respond effectively in complex mission environments. Operators do not want to be distracted from their mission and the time it takes them to turn their attention to a possible threat could be too slow to save the vehicle.

Startle delivers local autonomy to a vehicle by providing a mechanism for machine situation awareness to efficiently detect and assess potential threats. This allows vehicle sensing and processing resources to be devoted to the assigned task, but if a threat is detected it will cue the other systems to deal with it swiftly before continuing its mission. These vital seconds could be the difference between mission failure and success.”

Roke told the Engineer that, “What we’re emulating is the mechanism that allows mammals to have focus of attention, concentrating on what their primary task is…. You’ve got a continuous stream of data that is being processed at quite a high level, looking at possible threats that it has been trained to detect,” said Hook. “If it sees something that matches that, it will seek to prove whether there is a threat or not. This is what drops the false alarm rate.”