Thanks to artificial intelligence, drones can now fly autonomously at remarkably high speeds, while navigating unpredictable, complex obstacles using only their onboard sensing and computation.
In a new study, researchers at the University of Zurich have trained an autonomous quadrotor to fly through previously unseen environments – such as forests, buildings, ruins, and trains – keeping speeds of up to 40 km/h and without crashing into trees, walls, or other obstacles.
This feat was achieved by getting the drone’s neural network to learn flying by watching a sort of “simulated expert” – an algorithm that flew a computer-generated drone through a simulated environment full of complex obstacles. Now, this “expert” could not be used outside of simulation, but its data was used to teach the neural network how to predict the best trajectory, based only on the data from the sensors.
The research team says that this approach offers a significant advantage over existing systems, which first use sensor data to create a map of the environment and then plan trajectories within the map – two steps that require time and make it impossible to fly at high speeds. As Davide Scaramuzza, who leads the Robotics and Perception Group at the University of Zurich, explains:
To master autonomous agile flight, you need to understand the environment in a split second to fly the drone along collision-free paths. This is very difficult both for humans and for machines. Expert human pilots can reach this level after years of perseverance and training. But machines still struggle.
Autonomous drones that are not constrained by speed or the absence of a planned trajectory could prove useful in emergencies, on construction sites, or for security applications.
Incidentally, the same approach could be used for improving the performance of autonomous cars, or could even open the door to a new way of training AI systems for operations in domains where collecting data is difficult or impossible – on other planets, for example.
The researchers say the next steps will be to make the drone improve from experience, as well as to develop faster sensors that can provide more information about the environment in a smaller amount of time – thus allowing the machines to fly safely even at speeds above 40 km/h.
FTC: DroneDJ is reader supported, we may earn income on affiliate links