DigestAI news desk

Cut through the AI noise.

Research3 min read

Google DeepMind tests Gemini 4 Argon on Apollo 2 humanoid in internal test

google deepmind’s robotics team used gemini 4 argon to watch a video of a human playing cornhole. the model built a virtual simulation in mujoCo and calculated the physics needed for apptronik’s apollo 2 humanoid to sink seven consecutive shots in the real world. this video‑to‑sim‑to‑real pipeline compresses weeks of manual modeling into a few hours, turning ordinary videos into an infinite…

1 source

Key points

  • google deepmind uses gemini 4 argon to build a virtual simulation of apollo 2 humanoid in mujoCo
  • nasa’s perseverance rover has driven 28.10 miles, surpassing opportunity’s 28.06 miles
  • microducks synchronize over bluetooth to compose songs on the fly

nasa’s perseverance rover has driven 28.10 miles (45.22 kilometers) on mars, surpassing opportunity’s 28.06 miles (45.16 kilometers). the record was set on the 2,006th martian day of its mission, covering five and a half years.

other highlights include microducks that sync over bluetooth to compose songs on the fly, and a kamino simulation software that accelerates physics for complex mechanical systems.

Model page: Gemini 4 Argon →

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

Video Friday: When Two Robots Become One

IEEE Spectrum Robotics · 16 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
Google DeepMindPollenNASABoston DynamicsDEEP RoboticsDisney ResearchGemini 4 ArgonApollo 2MuJoCoKamino simulation softwareKeisuke

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 Research

All →

Related stories