DeepMind's Gemini Robotics 2 adds full-body control to humanoid robots
Source published ·Modelwire updated
Original coverage: The Verge - AI ↗·How Modelwire adds context

The development
Google DeepMind's Gemini Robotics 2 expands from upper-body control to full-body coordination, marking a meaningful step toward embodied AI systems that can execute complex, multi-limb tasks. This capability jump signals the field's progress in translating foundation model reasoning into real-world robotic manipulation and locomotion. For roboticists and hardware companies, the shift from isolated limb control to integrated whole-body motion reduces engineering friction and accelerates deployment timelines. The move also underscores DeepMind's strategy to position Gemini as a general-purpose embodied intelligence layer, competing directly with emerging robotics-focused AI startups.
Modelwire’s AI-generated summary of coverage from The Verge - AI.
Modelwire analysis
Analyst takeOur AI-generated reading of the wider context and the next developments to watch.
The buried detail here is that whole-body control has historically been the hard wall separating demonstration robots from deployable ones. DeepMind clearing that bar with a foundation model, rather than task-specific controllers, matters less as a research result and more as a signal about which companies now have a credible path to hardware partnerships at scale.
This is largely disconnected from recent activity in our archive, so context has to come from the broader space. The competitive frame belongs alongside the ongoing consolidation between large foundation model labs and robotics hardware companies, a dynamic that has accelerated through 2025 and into 2026 as firms like Figure, Physical Intelligence, and Apptronik have each sought AI backbone partners. DeepMind positioning Gemini as that backbone, rather than licensing to a single OEM, is a platform bet. It means DeepMind wants margin from the intelligence layer across many hardware vendors, not from any single robot product.
Watch whether a named hardware partner, particularly one already in the Alphabet portfolio or a prior DeepMind pilot, announces a commercial deployment using Gemini Robotics 2 within the next six months. That would confirm the platform strategy is converting to real contracts rather than staying in the demo phase.
This interpretation is generated from the summary above and available source metadata. Our methodology · Report an error
MentionsGoogle DeepMind · Gemini Robotics · Gemini Robotics 2
How this coverage is produced
Modelwire uses AI to generate summaries and context from source headlines, snippets, and selected archive coverage. Automated checks do not verify every claim, and items are not routinely reviewed by a person before publication. Zacaria Solis operates the site. Read the linked source for the full evidence and report errors through our corrections process.
Modelwire summarizes, we don’t republish. The Verge - AI originally reported this story as “Google DeepMind’s new AI model can control a robot’s entire body”. The full content lives on theverge.com. If you’re a publisher and want a different summarization policy for your work, see our takedown page.