Artificial intelligence (AI) is the next city in the competition with humans, this time in the field of drone racing. The relevant paper was published in the UK journal Nature on the 30th. Researchers from institutions such as the University of Zurich in Switzerland have developed an artificial intelligence system called Swift based on deep reinforcement learning. The system's ability to control drones can defeat top human players in one-on-one competitions. Artificial intelligence has already defeated humans in games such as chess and StarCraft, but these are all chess or electronic games rather than real-world competitions. In this first person perspective drone race between artificial intelligence and humans, contestants need to control a high-speed (up to 100 kilometers per hour) drone to cross the 3D track, observe the surrounding environment from the drone's perspective and control it through live video footage from an onboard camera throughout the entire process. This is more unpredictable than chess and electronic games, and is not an easy task for artificial intelligence. It is reported that this artificial intelligence system combines deep reinforcement learning strategies with data collected from the real world, defeating three human players who have won the first person perspective drone race championship, winning a total of 15 out of 25 games, and breaking the record for the shortest time spent in the race, leading the best performance of the human player by half a second. The research team stated that this is a milestone in the development of artificial intelligence and will contribute to the research and development of autonomous vehicles, robots and other related fields. (New News Agency)