Google DeepMind has released Gemini Robotics 2, a software stack that moves robot control beyond simple table-top tasks to include whole-body movement, five-fingered dexterity, and coordination between multiple robots. The release arrives as three distinct models with varying access levels. Most current robots rely on pre-programmed routines or remote operation for narrow tasks. They fail to adapt to unpredictable environments, and skills rarely transfer between different robot bodies. Gemini Robotics 2 aims to address all three limitations simultaneously.
Three models and their functions
Gemini Robotics 2
This vision-language-action (VLA) model converts visual and language input into motor control. It drives full humanoids from feet to fingertips and manages other two-armed robots. It also handles dexterous manipulation on both multi-finger hands and parallel grippers.
Gemini Robotics ER 2
Known as the embodied reasoning model, this vision-language system acts as the high-level brain. It communicates with humans, understands the physical world, and plans multi-step tasks lasting several minutes. Based on Gemini 3.5 Flash, the model accepts interleaved text, image, video, and audio with a context window of up to 128k tokens, emitting text up to 64K tokens. It is currently in public preview.
Gemini Robotics On-Device 2
This efficient VLA model is optimised to run locally on the robot itself. Built on Gemini Robotics 1.5 technology and Google’s on-device Gemma models, it takes text, images, and robot proprioception as numerical values. Its output consists of robot actions as numerical values. This version remains gated.
The division of labour is critical for system design. ER 2 plans and tracks the task, then hands motor execution to a VLA declared as a tool. Developers register low-level control interfaces, such as VLA models or navigation APIs, as callable tools. They then stream multimodal video, audio, or text directly into the model.
Whole body control on Apptronik Apollo 2
Previous Gemini Robotics models controlled only the humanoid’s upper body for table-top tasks. Gemini Robotics 2 extends control to whole-body motion for the first time.
The worked example uses Apptronik’s Apollo 2. Given the instruction “put the watering can into the green bin in the bottom shelf,” Apollo walks to the table and picks up the watering can. It then takes a few steps to the shelves and places the object at its destination.
Google DeepMind is direct about the remaining gap. It states that its robots have more to advance in movement speed.
Dexterity across hands and grippers
Gemini Robotics 2 can control the five-fingered, 22 degree-of-freedom SharpaWave hand on Apollo 2. Reported actions include tying knots and sealing a ziplock bag. The same model also operates standard two-fingered parallel grippers on a Franka Duo platform for tasks like tight packing.
The reported success rates come from one model checkpoint controlling three embodiments: Apollo 2 with SharpaWave hands, Apollo 2 with Inspire hands, and Franka Duo with a Robotiq gripper.
| Category | Embodiment | Task | Success |
|---|---|---|---|
| General whole body manipulation | Apollo 2 + Inspire hands | Pick up from shelf | 76.3% |
| General whole body manipulation | Apollo 2 + Inspire hands | Pick up from table | 68.4% |
| General whole body manipulation | Apollo 2 + Inspire hands | Pick up from floor | 45.7% |
| Multi-finger dexterity | Apollo 2 + Sharpa hands | Unscrew bulb | 92% |
| Multi-finger dexterity | Apollo 2 + Sharpa hands | Tie trash bag | 44% |
| Multi-finger dexterity | Apollo 2 + Sharpa hands | Ziplock | 40% |
| Multi-finger dexterity | Apollo 2 + Sharpa hands | Screw bulb | 36% |
| Multi-finger dexterity | Apollo 2 + Sharpa hands | Dustpan | 32% |
| Gripper dexterity | Franka Duo | Precise insertion tasks | 89.6% |
| Gripper dexterity | Franka Duo | Diverse tool kitting | 78.9% |
| Gripper dexterity | Franka Duo | General pick and place | 74.2% |
ER 2: Temporal intelligence and tool orchestration
The developer X post focuses on a problem that rarely gets benchmarked: knowing when a task is actually done.
Progress classification
Each frame in a video feed is assigned to one of five progress levels, from 0-20% through 80-100%. Gemini Robotics ER 2 reaches 57.4% accuracy on this task. Google DeepMind reports this outperforms previous generation models and competing frontier models.
Moment finding
This measures whether the model can identify the exact frame where a critical event occurs. An example is the moment to stop pouring coffee into a cup. ER 2 reaches 91.3% accuracy with a 0.96 second mean absolute distance. Google DeepMind reports it competing closely with much larger model categories at 4x the execution speed.
Tool orchestration
ER 2 is evaluated across three control modes: real VLA, sim VLA, and human tele-op. It outperforms Gemini Robotics ER 1.6 on all three.
ER 2 integrates with the Gemini Live API through a bidirectional streaming endpoint. The stated purpose is removing the stop-and-think pauses that break multi-step execution. It can also natively call tools like Google Search or any user-defined function.
Three spatial capabilities were upgraded. Success and failure detection now runs on raw video feeds instead of static snapshots, which catches mid-execution spills and slips. General instrument reading extends beyond circular dials to digital displays, linear scales, rulers and liquid thermometers, tested across 10 instrument types. Spatial visual question answering improves through Gemini’s multimodal advances.
Google DeepMind built a demo with Spot from Boston Dynamics, using ER 2 to orchestrate Spot navigation and manipulator APIs. Sample code is available in the robotics-samples repository.
Multi-robot collaboration
Gemini Robotics 2 introduces collaboration between different robot types. The reasoning is that no single robot fits every task. A wheeled rover suits indoor work, while a humanoid handles uneven terrain better.
Robots communicate through a shared semantic understanding to hand off subtasks. The demonstrated pairing is Apptronik’s Apollo 2 with a Franka F3 Duo.
On-Device 2: Adapting to new robot bodies
Gemini Robotics On-Device 2 targets applications that cannot rely on network latency or connectivity. It is natively multi-embodiment and inherits the motion transfer techniques from Gemini Robotics 1.5.
Google DeepMind reports adaptation to new bi-arm embodiments in a few hours, typically with fewer than 200 examples. This holds for embodiments with drastically different shapes, sensors and degrees of freedom. Demonstrated platforms include Dexmate, SO101 and Trossen.
The model card publishes a data scaling comparison against On-Device 1 on platforms introduced only during post-training:
| Platform | Model | Start | End |
|---|---|---|---|
| SO101 | On-Device 2 | 6.7% | 53.3% |
| SO101 | On-Device 1 | 0.0% | 6.7% |
| Dexmate | On-Device 2 | 24.4% | 75.6% |
| Dexmate | On-Device 1 | 13.3% | 33.3% |
The SO101 result is the sharper one. On-Device 1 barely leaves the floor, while On-Device 2 crosses 50%.
The model card also lists limits. On-Device 2 is limited in generalizing to out-of-distribution tasks and in controlling high-degree-of-freedom robots.
Availability
Gemini Robotics ER 2 is available for public preview. The VLA and on-device models remain gated.
ASIMOV-Agentic, a new safety benchmark, is on Hugging Face under CC-BY-4.0.
