Search results

The widespread use of drones among the general public has led to an alarming increase in accidents, some with lethal consequences. As drone blades are made from rigid materials and rotate at very high speeds, their impact with a human body can result in fatal injuries. Reliable collision detection combined with near-instantaneous braking of the drone’s rotor(s) can substantially lessen the severity of injuries sustained. The purpose of this paper is to achieve a safety solution which can be easily integrated into new products, or retrofitted into existing systems.

Through a proof of concept, this paper demonstrates the possibility of detecting a collision with a drone propeller absent any hardware modifications to the drone’s instrumentation. The solution relies on current-sensor readings, ordinarily used for monitoring the battery status of electrically actuated drones. The braking is achieved purely by reconfiguring the motor’s control strategy, without the need for additional hardware, as has been the case in previous works.

This paper demonstrates the possibility of detecting a collision with a drone propeller absent any hardware modifications to the drone’s instrumentation.

Compared to previous works which require installing additional hardware, the solution is purely software. This makes it very easy to integrate into existing systems or new products, at no additional cost. In experiments conducted on a prototype system, the solution was shown capable of detecting a collision and braking the motor in fewer than 20 ms. This allowed attenuating centimetre-deep cuts made to a piece of meat by an unprotected rotor to mere superficial scratches.

This paper aims to present a new vision-based approach for both the identification and the estimation of the relative distance between the unmanned aerial vehicle (UAV) and power pylon. Autonomous power line inspection using small UAVs, has been the focus of many research works over the past couple of decades. Automatic detection of power pylons is a primary requirement to achieve such autonomous systems. It is still a challenging task due to the complex geometry and cluttered background of these structures.

The identification solution proposed, avoids the complexity of classic object recognition techniques. Instead of searching the whole image for the pylon template, low-level geometric priors with robust colour attributes are combined to remove the pylon background. The depth estimation, on the other hand, is based on a new concept which exploits the ego-motion of the inspection UAV to estimate its distance from the pylon using just a monocular camera.

An algorithm is tested on a quadrotor UAV, using different kinds of metallic power pylons. Both simulation and real-world experiments, conducted in different backgrounds and illumination conditions, show very promising results.

In the real tests carried out, the Inertial Navigation System (INS) of the vehicle was used to estimate its ego-motion. A more reliable solution should be considered for longer distances, by either fusing INS and global positioning system data or using visual navigation techniques such as visual odometry.

A simple yet efficient solution is proposed that allows the UAV to reliably identify the pylon, with still a low processing cost. Considering a monocular solution is a major advantage, given the limited payload and processing power of such small vehicles.