VFF - The signal in the noise
Model ReleaseTrending

Google DeepMind Releases Gemini Robotics 2 for Whole-Body Robot Control

Read original
Share
Google DeepMind Releases Gemini Robotics 2 for Whole-Body Robot Control

Google DeepMind introduced Gemini Robotics 2, a suite of AI models designed to give robots whole-body control, dexterous manipulation, and multi-robot collaboration capabilities. The system includes three models: a vision-language-action model for motor control, an embodied reasoning model for planning and communication, and an on-device model optimized for fast adaptation to new robot bodies. Early-access partners can now deploy these models on humanoid and bi-arm robots to perform complex, multi-step tasks in unstructured environments.

  • Gemini Robotics 2 enables full-body humanoid control, including walking, crouching, and object manipulation, moving beyond previous upper-body-only capabilities
  • The system includes three models: a VLA for motor control, an embodied reasoning model for multi-step planning and human communication, and an on-device model for local deployment
  • The on-device model can adapt to entirely new robot embodiments in just a few hours of data, addressing a long-standing challenge in robot skill transfer
  • Multi-robot collaboration is now supported, allowing robots to coordinate on tasks, and the models can run locally on robotic hardware

Most deployed robots today are pre-programmed or teleoperated for narrow tasks and cannot adapt to unpredictable environments. Gemini Robotics 2 addresses this by giving robots the ability to reason through movements, understand context, and learn new embodiments rapidly. This represents a step toward robots that can operate autonomously in real-world, unstructured settings like homes and workplaces.

Organizations deploying robotic systems face high costs when retraining models for different robot bodies or new tasks. Fast adaptation to new embodiments and the ability to run models locally on devices reduces dependency on cloud infrastructure and accelerates deployment timelines. Multi-robot coordination also enables more complex workflows without proportional increases in programming overhead.

  • Robot manufacturers and integrators can now deploy the same model checkpoint across different robot bodies and hand designs, reducing fragmentation in the robotics ecosystem
  • On-device inference capability reduces latency and cloud dependency, making robots more suitable for real-time, safety-critical applications
  • Embodied reasoning and multi-robot collaboration open new use cases in complex, multi-step tasks that previously required human oversight or teleoperation
  • The challenge of multi-finger dexterous manipulation remains unsolved, limiting applicability to tasks requiring fine-grained hand control

Monitor deployment outcomes from early-access partners to assess real-world performance on complex tasks and whether the few-hours adaptation claim holds across diverse robot morphologies. Watch for announcements on which robot manufacturers integrate these models and whether performance on multi-finger dexterous tasks improves in future iterations. Track whether on-device inference becomes the standard for production deployments or if cloud-based reasoning remains necessary for complex planning.

Related Video

Share

Subscribe to the newsletter

The latest stories and analysis, delivered to your inbox.

Free. No spam. Unsubscribe any time.

Related stories

Google AI Overviews Now Appear in 43% of Searches

Google AI Overviews Now Appear in 43% of Searches

Google's AI Overviews now appear in 43% of searches, marking a significant shift in how users encounter information online. The feature, which provides AI-generated answers directly in search results, has achieved rapid adoption since its introduction. This trend reflects a broader move toward AI-mediated information discovery rather than traditional link-based search results.

by Sarah Perez· TechCrunch AI
Google Designs Custom Chip to Embed Gemini, Boost AI Efficiency
TrendingNews

Google Designs Custom Chip to Embed Gemini, Boost AI Efficiency

Google is developing a custom server chip called 'Frozen v2' that would embed its Gemini AI model architecture directly into hardware to improve inference efficiency. The chip is projected to be 6 to 10 times more efficient than Google's current homegrown AI chips when measured by tokens served per unit of power. The project addresses a critical compute capacity shortage that has strained Google Cloud's ability to serve external customers.

by Qianer Liu· The Information
Google Vids adds AI avatars for personalized video creation
TrendingNews

Google Vids adds AI avatars for personalized video creation

Google has added personalized AI avatars to its Vids product, enabling users to create videos featuring digital versions of themselves. The feature integrates with Gemini Omni-powered tools that generate and edit videos from text prompts and reference images. This expands Google's video creation capabilities beyond text-to-video generation to include avatar-based personalization.

by Sarah Perez· TechCrunch AI
DeepMind Researcher Raises $300M Pre-Seed on Visual AI Vision

DeepMind Researcher Raises $300M Pre-Seed on Visual AI Vision

Andrew Dai, a former DeepMind researcher who contributed to foundational AI research that influenced ChatGPT's development, has raised funding at a $300 million pre-seed valuation before launching a product. Dai is positioning visual AI as a major frontier in artificial intelligence development. The funding round reflects investor confidence in his track record and vision, though the company remains pre-launch.

by Maggie Nye· TechCrunch AI