DigestAI news desk

Cut through the AI noise.

Robotics & Physical AI4 min read

ETH Zurich quadruped robot solves giant Rubik’s Cube using only its feet

ETH Zurich Robotics Systems Lab released a video showing a quadruped robot autonomously solving a giant Rubik’s Cube using only its feet. The robot follows a three‑stage framework called Reflex that learns visual reactive whole‑body control step by step, linking stages through a compact object‑dynamics representation.

1 source

Key points

  • ETH Zurich Robotics Systems Lab’s quadruped solves a giant Rubik’s Cube using only its feet.
  • The robot uses the three‑stage Reflex framework for visual reactive whole‑body control.
  • The video is featured in IEEE Spectrum’s “Video Friday” series showcasing advanced loco‑manipulation.

The demonstration highlights the robot’s ability to anticipate and react to a moving target within about a second, a capability that remains difficult for humanoid platforms. The video appears in IEEE Spectrum’s “Video Friday” series, which also referenced KAIST’s humanoid pushing objects up to 35 kg, AthenaZero’s fingers closing in about 80 milliseconds, and ETH Zurich’s bio‑hybrid actuators.

Researchers suggest the Reflex approach could be applied to tasks such as robot laundry folding or other manipulation problems, though the article does not provide quantitative performance metrics beyond the visual success of the Rubik’s Cube solve.

Full story from IEEE Spectrum Robotics · by Evan AckermanOpen source ↗

Video Friday: Quadruped Robot Solves Giant Rubik’s Cube By Itself

IEEE Spectrum Robotics · 23 October 2026

Loading the full article…

This text was published by IEEE Spectrum Robotics and written by Evan Ackerman. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗

Topics · follow one to build your own front page
ETH Zurich Robotics Systems LabIEEE SpectrumWeikaiMichael Perry

The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.

Comments

via GitHub Discussions

More in Robotics & Physical AI

All →

Related stories