“We are trying to develop robots that are more human-like in how they explore,” Girdhar said. “With a curious robot, the idea is that you can just let it go, and it will begin to not only collect visual data like traditional underwater robots, but make sense of the data in real time and detect what is interesting or surprising in a particular scene. The technology has the potential to dramatically streamline the way oceanographic research is done.”
Girdhar programmed his algorithm into Aqua, a six-flippered robot designed to explore shallow-depth attractions such as coral reefs and the undersides of ship hulls, and deployed it in the waters off the Bellairs Research Institute in Barbados.
As Aqua travels, it learns to recognise new objects, while watching out for things that don’t quite belong. The anomalous objects are tagged as the most interesting, causing the robot to head over and take a closer look.
“I went scuba diving with Aqua, completely unsure of what to expect,” Girdhar said. “We let it go near a coral head surrounded by mountainous sand. It didn’t take long before we noticed that it was more attracted to the coral head. It had very animal-like behaviour and started sniffing around like a dog. It didn’t want to go near the sand, since that wasn’t as interesting.”
When Girdhar himself swam into the field of view of Aqua, it followed him until he stopped swimming, at which point the robot hovered around him.
Girdhar’s algorithm is proposed to speed underwater research by stopping the robots from producing thousand of images, most of which contain nothing of scientific interest.
The researchers now plan to try the algorithm in more complex robots in actual research missions.
