Gemini Robotics 2とは？人型ロボットの全身を操る新モデル

Most robots are pre-programmed or teleoperated for narrow, repetitive task sequences. They lack the ability to truly learn for themselves or adapt to unpredictable environments. Moreover, transferring learned skills from one robot body to another remains incredibly difficult. ／ Today, we are introducing Gemini Robotics 2 - the intelligence layer powering the next generation of truly adaptable robots. — 従来のロボット制御が抱える課題と、Gemini Robotics 2 の位置づけに関する記述より

While our previous models controlled the humanoid’s upper-body to achieve table-top tasks, Gemini Robotics 2 expands physical AI into whole-body motions. ／ Apollo processes the instruction, walks to the table, and picks up the watering can, takes a few steps to the shelves, and places it precisely in its destination. While our robots have more to advance in movement speed, this is an important step towards the skills needed to complete more complex, real-world tasks that require whole-body coordination. — 制御範囲の拡張、実演タスク、動作速度に関する留保の記述より

Gemini Robotics 2: Our most advanced vision-language-action model (VLA) that converts vision and language input into motor control, enabling a robot to take action. This model is capable of controlling full humanoids, from feet to fingertips, and other bi-arm robots. It also brings a new level of dexterous manipulation on both hands and grippers. — VLA モデルの定義と対応する機体の記述より

Gemini Robotics ER 2: Our most capable embodied reasoning (ER) model. It is a vision language model (VLM) that acts as our agent, enabling robots to communicate with humans, understand the physical world and plan multi-step tasks lasting several minutes. ／ It observes the room, reasons about the steps needed to complete the task, coordinates with the VLA to carry out the actions, and tracks progress until the task is done. This setup allows robots to execute complex multi-step tasks, self-correct if a step fails, and generalize to novel situations and goals. ／ In this update, we are enabling robots to more reliably execute longer task sequences, lasting several minutes and involving hundreds of decisions. ／ Gemini Robotics On-Device 2: Our most efficient vision-language-action model (VLA) optimized to run locally on robotic devices. This model can now achieve fast adaptation to completely new robot embodiments with a few hours of data. ／ This model is natively multi-embodiment and inherits our advanced "motion transfer" techniques from Gemini Robotics 1.5. We can now adapt to new bi-arm robot embodiments with just a few hours of adaptation time, typically with less than 200 examples. This works even with new embodiments with drastically different shapes, sensors and degrees of freedom, as shown below with a diverse set of tasks being performed by the Dexmate, SO101, and Trossen platforms. — ER 2 と On-Device 2 の種別・担当範囲、ER 2 の手順実行、適応速度と対象プラットフォームの記述より

For example, it can enable a humanoid to walk, crouch, stretch, and manipulate objects to clean up a cluttered room. It can even team up with other robots to finish the job faster. ／ Gemini Robotics ER 2 now understands when tasks begin and end, and can pinpoint the moment key events occur, marking a step change in progress understanding. ／ 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. — 片付けの例、作業の開始・終了の理解、および多ロボット協調の導入に関する記述より

Gemini Robotics 2 controlling three different embodiments, using the same model checkpoint — the Apptronik Apollo 2 robot with SharpaWave hands, the Apollo 2 robot with Inspire hands, and the Franka Duo with the Robotiq gripper — on a wide variety of whole-body and dexterous manipulation tasks. ／ The model can now control the five-fingered, 22 degree-of-freedom SharpaWave hand on the Apollo 2 robot to complete delicate actions like tying knots or sealing a ziplock bag. It can also operate standard two-fingered parallel grippers on a Franka Duo platform to perform complex dexterous tasks (e.g. tight packing). — 単一チェックポイントによる3機体制御、および SharpaWave ハンドと2本指グリッパの作業例の記述より

While Gemini Robotics 2 achieves a medium to high success rate for whole-body and gripper-based dexterous tasks, the multi-finger dexterous manipulation remains challenging. ／ We are continuing to advance the level of precision and speed to achieve human-level dexterity. ／ We’re introducing ASIMOV-Agentic , a new benchmark for agentic safety orchestration and uncertainty resolution. For example, it measures the embodied reasoning agent’s ability to refuse unsafe tool calls from a VLA.It also measures the agent’s ability to predict whether a task is possible and to proactively request human intervention when uncertain. ／ Additionally, with enhanced embodied reasoning, Gemini Robotics ER 2 is our safest robotics model to date in safety constraint following and human proximity benchmarks. 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. This is a key requirement in collaborative safety standards. — 多指操作の課題、速度と精度、ASIMOV-Agentic の測定対象、および人との近接に関する安全性能の記述より

Gemini Robotics ER 2, our reasoning model, is now available on Google AI Studio and in private preview on Gemini Enterprise Agent Platform. Our VLA and On-Device models are available to early-access partners. ／ Sign up for our Trusted Tester Program ／ Gemini Robotics 2 marks an important milestone on the path toward solving AGI in the physical world. Unlocking the true potential of robotics requires moving past single-task automation toward general-purpose intelligence. — 3モデルの提供状況、Trusted Tester Program、汎用的な物理AIへの位置づけに関する記述より