Consumer DBUS2 drone features new autonomous flight technology

By Patrick C. Miller | March 25, 2019

The DBUS2 is the first consumer drone equipped with visual inertial odometry (VIO), a new technology that enables drones to navigate on their own without human input.

Designed by Drones by US (DbUS) of Santa Clara, California, the $390 DBUS2 uses a camera for odometry, inertial motion sensors and software to recognize object shapes and determine where the drone is. DbUS calls its drone the first step on the road to autonomous flight.

The DBUS2 is an advanced aircraft with a 4K camera, follow-me and autoflight functions that into a pocket or kit bag. According to DbUS, VIO gives drones the ability to see safe paths through buildings, recognize optimum landing spots and navigate inside structures without GPS, enabling it to take on more tasks because there’s less need for human intervention.

The main components of the DBUS2's VIO system are a single 160-degree, ultra-wide-angle camera, inertial motion sensors and sophisticated software. Inertial sensors measure absolute scale, but they can be subject to drift when small positioning errors become magnified over time. The VIO algorithms compensate for this, using scale from the inertial sensors and positioning from the camera to tell the drone where it is in relation to its environment.

VIO enables DBUS2 to hover accurately within plus or minus 3.8 inches, maintain its position and fly back to its hover point, even if it's been pulled away. The DBUS2's memory cruise feature uses VIO to store the coordinates of where it is. The drone can play back the coordinates to repeat a flight. It can also play them in reverse, enabling the drone to fly back home no matter how windy or narrow the route. Memory cruise can record even when the motors are off, enabling operators to hold the aircraft while they walk with it to memorize a flight path.

VIO systems use a camera to take an image of what it sees ahead and below. For selected frames, image processing software builds a point cloud (a set of data points in space) around the edges of each meaningful shape in the frame, marking where it is in the frame.

At the same time, VIO uses the drone's inertial motion unit to track its movement in space, such as up or down, back or forward, left or right. These sensitive sensors know where the drone is relative to itself and its travel—from millisecond to millisecond.

GPS data is on the horizon for VIO in small drones, which will include an awareness of no-fly zones and other restricted airspace. There’s also potential integration with terrain databases and with LAANC, the system for obtaining permission to fly near airports.

DbUS expects that as VIO evolves, it will recognize textures and fine movements better, along with fine movements of objects it sees. Along with collision avoidance—using VIO, LIDAR, sonar and/or radar—and data from magnetic sensors and radio navigation, this suite enables drones to fly on their own, whether it's delivering a package, saving a life, inspecting a bridge or other tasks.