On the cover page of Nature: Champion-level drone racing using deep reinforcement learning
Today the research of Prof. Davide Scaramuzza and his group is on the cover of Nature (attached) for a research paper entitled "Champion-level drone racing using deep reinforcement learning".
The paper presents the first autonomous drone that beat the human world champions of drone racing. The races were quietly organized in summer 2022, but the research became only public today. This amazing 5-minute video explanation by Nature explains how it works.
Prof. Scaramuzza states this result is historical: Remember when IBM’s Deep Blue won against Gary Kasparov at chess in 1996, or when Google DeepMind’s AlphaGo won against the top champion Lee Sedol at Go in 2016? These competitions where AI algorithms prevailed over human champions are key milestones in the history of AI but they were limited to board games. The result of Prof. Scaramuzza's group marks the first time that an AI has beaten a human champion in a real physical sport designed for and by humans. As such, this result is a milestone for robotics, machine intelligence, and beyond.
The news is ramping up quickly: https://www.theguardian.com/technology/2023/aug/30/ai-powered-drone-beats-human-champion-pilots