A research team from Japan has developed a machine vision algorithm, making it possible for lightweight indoor drones to guide themselves by identifying and interpreting reference points.
According to the German news agency, the technology opens the door to a new breed of functional drones with potentially wide-ranging uses.
The team from the Shibaura Institute of Technology published its findings in the Journal of Automatica Sinica.
The Tech Xplore website cited lead author Chinthaka Premachandra as saying: “Since GPS signals are too weak to penetrate most structures, indoor drones must rely on environmental queues, which are typically visual.”
A drone designed for indoor use is likely to be smaller and lighter than an outdoor drone.
The prototype developed by Premachandra had a single camera connected to a visual sensor integrated with a processor containing the algorithm developed by the team.
The researchers explained that the algorithm allows the drone to extrapolate its position in the room, helping it avoid contacting the walls.
Premachandra said the next step is using infrared cameras so the drones could function in the dark.