at the University of Zurich, Swift outperformed human pilots 60% of the time, setting new lap records that no human competitor could match.\u00a0<\/span><\/p>\nThis technology may pave the way for faster and more efficient drones in various industrial applications.<\/span><\/p>\nDrone racing sees high-end quadcopters zoom through obstacle courses at break-neck speeds of over 100km\/h.\u00a0<\/span><\/p>\nPilots utilize headsets to view real-time footage captured by onboard HD cameras as they navigate drones through a series of gates. It\u2019s seriously impressive stuff, and you\u2019d be forgiven for thinking that human instincts are virtually irreplaceable here.\u00a0<\/span><\/p>\nBut that’s not the case, as the AI system Swift, which uses deep reinforcement learning (RL), was able to outcompete three top-level human competitors in a series of drone races.<\/span><\/p>\n\u201cIt managed to beat three top-level human pilots, including Alex Vanover, the 2019 Drone Racing League world champion, 60 per cent of the time,\u201d noted Leonard Bauersfeld, the lead researcher at the University of Zurich.\u00a0<\/span><\/p>\n