Nerian's Stereo Vision Technology Used for Autonomous MAVs
Agile Micro-aerial vehicles (MAVs) are required to operate in cluttered, unstructured environments at high speeds and low altitudes for efficient data gathering. Given the payload constraints and long range sensing requirements, cameras are the preferred sensing modality for MAVs. The computational burden of using cameras for obstacle sensing has forced the state of the art methods to construct world representations on a per frame basis, leading to myopic decision making. A long range perception and planning approach using cameras is mandatory. By utilizing the SP1 hardware system from Nerian for disparity calculation and image space to represent obstacles, the approach and system design of Carnegie Mellon University allows for construction of long term world representation whilst accounting for highly non-linear noise models in real time. These obstacle avoidance capabilities are demonstrated on a quadrotor flying through dense foliage at speeds of up to 4 m/s for a total of 1.6 hours of autonomous flights. This approach enables high speed navigation at low altitudes for MAVs for terrestrial scouting.
The full research paper is available at: