A group of researchers from the University of Zurich and Intel combined to come up with an AI pilot that ended up beating human champions at drone racing. The AI system, called Swift, won multiple races against three world-class champions in first-person view (FPV) drone racing. Pilots could fly quadcopters at speeds exceeding 100 km/h, controlling them remotely while wearing a headset linked to an onboard camera.
How was the AI ‘pilot’ trained?
In a press release, the University of Zurich said that Swift was trained in a simulated environment where it taught itself to fly by trial and error, using a type of machine learning called reinforcement learning. The use of simulation helped avoid destroying multiple drones in the early stages of learning when the system often crashes. The drone flew autonomously thanks to very precise positions provided by an external position-tracking system, while also recording data from its camera. This helped it to learn to autocorrect errors it made interpreting data from the onboard sensors.
How did it beat humans?
According to the university, this wasn’t the first time autonomous drones took on humans. However, earlier, they took twice as long as those piloted by humans to fly through a racetrack, unless they relied on an external position-tracking system to precisely control their trajectories. Swift, however, reacts in real time to the data collected by an onboard camera, like the one used by human racers, as per the university.
It has an integrated inertial measurement unit that measures acceleration and speed while an artificial neural network uses data from the camera to localise the drone in space and detect the gates along the racetrack.
Swift competed with the 2019 Drone Racing League champion Alex Vanover, the 2019 MultiGP Drone Racing champion Thomas Bitmatta, and three-times Swiss champion Marvin Schaepper. The races took place between June 5 and June 13 on a purpose-built track in a hangar of the Dübendorf Airport, near Zurich. The track covered an area of 25 by 25 meters, with seven square gates that had to be passed in the right order to complete a lap, including challenging maneuvers including a Split-S, an acrobatic feature that involves half-rolling the drone and executing a descending half-loop at full speed.
Swift achieved the fastest lap, with a half-second lead over the best lap by a human pilot. On the other hand, human pilots proved more adaptable than the autonomous drone, which failed when the conditions were different from what it was trained for.
How was the AI ‘pilot’ trained?
In a press release, the University of Zurich said that Swift was trained in a simulated environment where it taught itself to fly by trial and error, using a type of machine learning called reinforcement learning. The use of simulation helped avoid destroying multiple drones in the early stages of learning when the system often crashes. The drone flew autonomously thanks to very precise positions provided by an external position-tracking system, while also recording data from its camera. This helped it to learn to autocorrect errors it made interpreting data from the onboard sensors.
How did it beat humans?
According to the university, this wasn’t the first time autonomous drones took on humans. However, earlier, they took twice as long as those piloted by humans to fly through a racetrack, unless they relied on an external position-tracking system to precisely control their trajectories. Swift, however, reacts in real time to the data collected by an onboard camera, like the one used by human racers, as per the university.
It has an integrated inertial measurement unit that measures acceleration and speed while an artificial neural network uses data from the camera to localise the drone in space and detect the gates along the racetrack.
Swift competed with the 2019 Drone Racing League champion Alex Vanover, the 2019 MultiGP Drone Racing champion Thomas Bitmatta, and three-times Swiss champion Marvin Schaepper. The races took place between June 5 and June 13 on a purpose-built track in a hangar of the Dübendorf Airport, near Zurich. The track covered an area of 25 by 25 meters, with seven square gates that had to be passed in the right order to complete a lap, including challenging maneuvers including a Split-S, an acrobatic feature that involves half-rolling the drone and executing a descending half-loop at full speed.
Swift achieved the fastest lap, with a half-second lead over the best lap by a human pilot. On the other hand, human pilots proved more adaptable than the autonomous drone, which failed when the conditions were different from what it was trained for.
timesofindia.indiatimes.com
Source link