Skip to main content
See every side of every news story
Published loading...Updated

AI beats champion human pilots in head-to-head drone races

  • A team of researchers from the University of Zurich has developed an AI algorithm called Swift that defeated three world champion drone racers in head-to-head races. The algorithm, using deep reinforcement learning, learned to fly a drone around a 3D race course at high speeds without crashing too often. This marks the first time that AI has beaten a human champion in a physical sport.
  • Swift's technique enabled it to consistently start races faster and execute tighter turns than the human pilots. However, it lost 40% of the races against humans and was sensitive to changes in the environment, such as lighting. Despite the mixed feelings of the world champions, Swift's ability to cope with real-world challenges like aerodynamic turbulence and camera blur could have wider applications, such as drone search and rescue missions.
  • While the military has an interest in AI-powered drones, experts believe that the implications of Swift's victories in drone racing for warfare are uncertain. The advancements made in this research may have limited impact on military drones' critical processes like target selection, as they are mostly used in wide-open battlefields against stationary or slow-moving targets.
Insights by Ground AI

7 Articles

Think freely.Subscribe and get full access to Ground NewsSubscriptions start at $9.99/yearSubscribe

Bias Distribution

  • 80% of the sources are Center
80% Center

Factuality Info Icon

To view factuality data please Upgrade to Premium

Ownership

Info Icon

To view ownership data please Upgrade to Vantage

Nature broke the news in United Kingdom on Wednesday, August 30, 2023.
Too Big Arrow Icon
Sources are mostly out of (0)

Similar News Topics

News
Feed Dots Icon
For You
Search Icon
Search
Blindspot LogoBlindspotLocal