Robotics experts have successfully programmed robots to rescue dolls trapped in a three-dimensional maze, which simulates the aftermath of a natural disaster.
It became evident at the German Open, a warm-up event for the annual RoboCup Rescue competition.
A report about the event suggests that the robots use their sensing and mapping abilities to sniff out toy dolls, and to navigate the maze accordingly.
"The robots are the mouse and the dolls are the cheese," New Scientist quotes Adam Jacoff of the US Government's National Institute of Standards and Technology in Gaithersburg, US, who heads the rescue competition, as saying.
The 150-square-metre maze includes sharply pitched and sloping floors, stairs, pipes, and "step fields". It also has corridors of fixed, randomly shaped objects that simulate rubble.
Robots navigate the maze on their own, for their developers are not allowed inside the arena or to control their robots remotely.
Teams are scored by how many victims their robots finds, how quickly they navigate the maze, and how accurately they can generate a 3D map of the entire course.
Tom Haus, an urban search and rescue specialist at the US Government's Federal Emergency Management Agency, believes that autonomous robots still need a lot of improvement to be fit for search and rescue missions.
"They are still a ways away from having something as mobile as a human that could easily traverse rubble piles," he said.
He, however, said that the laser guidance systems, which the participants have developed for 3D imaging in the RoboCup Rescue competition, might be adapted for use by human rescuers much sooner.
"When you go into a dark, smoke-filled structure as a rescuer and then have to explain the layout to other rescuers, a lot is lost in translation. 3D mapping would be a huge benefit," Haus said.
Haus, one of the search and rescue experts that helped Jacoff develop the RoboCup Rescue maze, further said that the current scanning and map generation technology was too slow to be of much use for emergency response teams.