Gemini Robotics 2 brings whole body intelligence to robots
Gemini Robotics 2 brings whole body intelligence to robots
Google DeepMind has released Gemini Robotics 2, a new model that enables robots to perform complex tasks with whole-body intelligence, advanced dexterity, and multi-robot collaboration. The model supports real-time reasoning, on-device adaptation, and safety features for human-robot interaction.
Full article
You are reading the complete RoboSignal summary. The publisher’s full article is available at the original source.
Read full article at sourcedeepmind.google · Opens in a new tab; source language may differ.
Google DeepMind introduces Gemini Robotics 2, a significant advancement in whole-body control and multi-robot collaboration for embodied AI. The release highlights improvements in dexterity, reasoning, and on-device adaptation, with a focus on safety and real-world task execution.
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
What remains unknown
Not established in the collected evidence: Environment, Control, Data origin.
Reported performance applies to the described task. It does not establish general autonomy or deployment readiness.
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
From feet to fingertips — we are teaching robots intelligent whole-body control, fine dexterity, and teamwork to complete a broad range of complex tasks
Open source E1
Most robots are pre-programmed or teleoperated for narrow, repetitive task sequences
Open source E2
We demonstrated how Gemini's multimodal understanding could drive real-world action with Gemini Robotics
Open source E3
Gemini Robotics 2 enables robots to reason through every movement, unlocking a broad range of tasks
Open source E4
It can even team up with other robots to finish the job faster
Open source E5
Gemini Robotics On-Device 2 is built specifically to handle these constraints — it is our most-efficient vision-language-action model (VLA) optimized to run locally on robotic devices
Open source E6
This model is natively multi-embodiment and inherits our advanced “motion transfer” techniques from Gemini Robotics 1.5
Open source E7
We can now adapt to new bi-arm robot embodiments with just a few hours of adaptation time, typically with less than 200 examples
Open source E8
This works even with new embodiments with drastically different shapes, sensors and degrees of freedom
Open source E9
Gemini Robotics ER 2 now understands when tasks begin and end, and can pinpoint the moment key events occur
Open source E10
Furthermore, we are introducing multi-robot collaboration. This enables different types of robots to communicate and work together to solve complex workflows a single robot could not do alone
Open source E11
Gemini Robotics ER 2 is our safest robotics model to date in safety constraint following and human proximity benchmarks
Open source E12
It can better detect when humans are nearby, trigger safety tool calls and bring the robot to a safe stop if someone approaches too closely
Open source E13
Gemini Robotics 2 marks an important milestone on the path toward solving AGI in the physical world
Open source E14
Unlocking the true potential of robotics requires moving past single-task automation toward general-purpose intelligence
Open source E15
Implications for data suppliers
RoboSignal interpretation and collection questions, not statements of buyer demand.
- Confirm the required data type and collection setting with the buyer; this source does not establish a complete collection specification.
- Validate demand and acceptance criteria with a buyer before scaling. Publication, popularity and a research result do not establish a purchase commitment.
Source：Google DeepMind — Robotics · deepmind.google