A bright future for drones on farms

Research conducted by Dr Lauren Meiring of Stellenbosch University on the collision-avoidance systems of unmanned aerial vehicles such as drones could help boost the use of these machines on farms.

A bright future for drones on farms
The potential for drones colliding with each other or other aerial vehicles may be preventing farmers from using this technology more readily on their farms.
Photo: FW Archive
- Advertisement -

There is currently no commonly implemented collision-avoidance system that prevents intercollisions of unmanned aerial vehicles (UAVs), such as drones. This means that farmers may be reluctant to use these machines for fear of damage or other potential hazards.

Automation has also led to an increase in the use of drones in many fields. This boom has created the need for UAVs to fly in crowded airspaces and avoid colliding with each other.

Steering clear of collisions
Dr Lauren Meiring of Stellenbosch University (SU) recently obtained her doctorate in electronic engineering at SU. Her thesis, titled ‘Co-operative collision avoidance strategies for unmanned aerial vehicles’, focuses on possible ways to avoid collisions between UAVs.

- Advertisement -

Meiring developed and evaluated co-operative collision-avoidance algorithms for UAVs that are capable of avoiding short-term collisions with static and dynamic obstacles, as well as those between UAVs, while communicating their positions, velocities and intended flight trajectories in complex environments.

“Currently, there is no commonly implemented collision-avoidance system that prevents inter-UAV collisions. Some commercially available UAVs do implement collision avoidance, but only for static obstacles.

“When UAVs are equipped with inter-UAV collision-avoidance [systems], it is normally to achieve a specialised task and, as such, is not applicable to independent UAVs performing individual tasks,” says Meiring.

“These UAVs are assumed to be following long-term routes, such as flying between warehouses. When a collision is predicted along these routes, all UAVs co-operate to plan and execute short-term collision-avoidance trajectories. The UAVs use horizontal, vertical or three-dimensional manoeuvres to avoid collisions with one another, with static terrain and with dynamic obstacles,” she explains.

According to Meiring, current collision-avoidance technologies used in commercial airspace, namely traffic alert and collision-avoidance systems and ground proximity warning systems, are rules-based, non-co-operative and decoupled approaches that are not suitable for UAV collision avoidance in extremely congested airspace with complex terrain.

She says her approach doesn’t require the UAVs to be working together towards the same goal; they merely have to be in communication with each other and only co-operate for long enough to avoid a collision.

“The two algorithms I created are hybrids of the two most common approaches to collision avoidance, namely the centralised and decoupled approaches. In the centralised approach, all vehicles plan routes together to avoid the collision, and in the decoupled approach, this is done individually.

“Centralised strategies, while slow, are the most reliable and optimal; whereas the decoupled strategies are less reliable, but significantly faster.

My approach creates smaller groups of UAVs and plans the groups independently. The simulations I performed to test the effectiveness of my algorithms showed that both managed to improve on these strategies by eliminating some of their flaws while mostly retaining their strengths.”

Meiring says her research could also help to provide automatic collision avoidance for large numbers of drones delivering parcels to independent locations in an urban environment.

“Hopefully, this research will bring us a step closer to UAVs being integrated into more and more airspaces, especially commercial ones, by providing potential options to ensure collision avoidance.”