ainewsblitz.com

Breaking

Google DeepMind Unveils Gemini Robotics ER 2, an Embodied Reasoning Model That Reads Live Video to Catch Robot Mistakes

Google DeepMind Unveils Gemini Robotics ER 2, an Embodied Reasoning Model That Reads Live Video to Catch Robot Mistakes
  • Robotics
  • Foundation Models
  • AI Agents

Google DeepMind on July 30, 2026 introduced Gemini Robotics ER 2, an embodied reasoning model designed to act as the "high-level brain" for robots, capable of parsing continuous video feeds to detect mid-task failures such as spills, slips, and misalignments. The launch is part of the broader Gemini Robotics 2 family, which also includes the vision-language-action (VLA) model Gemini Robotics 2 and the compact Gemini Robotics On-Device 2.

Continue reading

The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.

$20
Read this article
$29/month
Unlimited — all 27,934 articles, the full archive, and comprehension quizzes
Save 72%
$98/year
≈ $8.17/month
Unlimited, billed once a year