Research · 7 Oct 2026 · Peer-reviewed / confirmed

Butterfly-inspired flapping robot gains lift after reinforcement-learning wing design

Purpose: sending the RankedRobot digest. Nothing else; never sold or shared for marketing.
What we keep: your email address, the date you signed up and the page you signed up on.
How long: until you unsubscribe, when the address is deleted. Before the first issue we email you once to confirm; addresses not confirmed within 30 days are deleted.
Who processes it: stored with Cloudflare, our host, which may process it outside your country. We'll name our email-sending provider in the privacy notice before the first issue.
Your choice: you don't have to subscribe; the only effect of saying no is that you won't get the digest. Unsubscribe any time.

Authors of an npj Robotics paper report optimised wing shapes raised lift by 339% and thrust by 46% on a 48 g robot.

A team including researchers at Beijing Information Science and Technology University has published an open-access paper in npj Robotics on optimising the wings of a robotic butterfly.

The authors built a flapping robot with adjustable wing geometry and measured how wing shape changes flight, using motion capture and a morphological comparison of 172 swallowtail (Papilionidae) butterflies. They then used deep reinforcement learning to search the wing design space.

The authors report that the optimised designs increased lift by 339% and thrust by 46%, and that physical flight tests matched the learned predictions to within 7%. The robot weighs 48.3 g, has a 57.5 cm wingspan and flaps at up to 5 Hz. The results come from 95 replicate experiments on 19 wing samples, in a laboratory setting.

Sources

npj Robotics (article, DOI 10.1038/s44182-026-00116-w)

Written by the RankedRobot news desk (AI-assisted, human-reviewed) from the sources above; checked 2026-10-12. Claims are attributed to whoever makes them. Spotted an error? corrections@rankedrobot.com