An international research project is creating the foundations for the next collision detection sensor systems in drones – inspired by the brain activity of swarming insects.
From delivering parcels to facilitating precision farming, the enormous potential for drones has seen global demand soar, according to the team. As such, there is a need for low-cost solutions to ensure the safe flight in dynamic environments such as cities, where buildings, cables and people create a risk of collision.
Coordinated by the University of Lincoln, the STEP2DYNA project has brought together 11 research teams, including neurobiologists, chip designers, robotics researchers and engineers from Europe and East Asia.
The five-and-a-half-year long project received funding from the European Union’s Horizon 2020 research and innovation programme. It is due to conclude later this year having produced multiple peer-reviewed research articles and conference papers, which aim to advance the discipline of robotic vision systems.
Researchers have used specialist technology to monitor the visual perception of insects to understand how they rapidly respond to looming objects. The team has analysed a special neuron within a locust brain that prevents large swarms of the species from colliding in a matter of milliseconds.
Biological patterns such as this will help to build a digital blueprint for drone sensor systems, enabling the vehicles to automatically detect and respond to obstructions in real time.
Shigang Yue, professor of computer science at the University of Lincoln, said: “Flight safety is a critically important aspect of drone development.
“This project has provided us with the opportunity to work with teams in different countries and across various disciplines to develop bio-inspired methods for drones to detect and avoid imminent collisions whilst flying.
“Our hope is that the algorithms developed by the consortium will be used by the industry to ensure the safety of drones in the future.”
