Google DeepMind Unveils Gemini Robotics 2 for Full-Body Control of Humanoid Robots
- Published
- Source
- TheVerge.com
Google DeepMind has announced the launch of Gemini Robotics 2, an advanced AI model capable of controlling humanoid robots from 'feet to fingertips.' This new version enhances the robot's ability to perform a variety of actions, including walking, crouching, and manipulating objects, significantly expanding its functional capabilities.
The importance of this development lies in its potential to enable humanoid robots to undertake more complex, real-world tasks that require whole-body coordination. With improved dexterity, Gemini Robotics 2 allows robots to perform intricate tasks such as sealing bags and unscrewing lightbulbs, marking a significant advancement in robotic manipulation.
Looking ahead, Google DeepMind is also enhancing its Gemini Robotics ER model, which aids robots in analyzing their environment and executing multi-step tasks. This update aims to improve collaboration among different types of robots, enhancing safety features and operational efficiency. No further timeline was disclosed at the time of publication.
Original report
Google DeepMind’s new AI model can control a robot’s entire body
TheVerge.com · Emma RothThis briefing is an independently written summary based on publicly available reporting and is provided for industry information and news discovery. The original report and source publication are credited and linked where applicable. RobotToday does not claim ownership of third-party source material.
Rights concerns? Contact [email protected] with the relevant URL and details. We will review the matter and take appropriate action where warranted.
More related news
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11
- 12
Related Suppliers
Google DeepMind
United Kingdom
Alphabet's London-based AI lab, developer of the Gemini Robotics vision-language-action models and the open-source MuJoCo physics simulator.
TRON K.K.
Japan
Tokyo humanoid integrator (est. 2024) bringing physical-AI robots, simulation training and Prevu3D factory digital twins to Japanese manufacturers.
Apptronik
United States
Austin, Texas humanoid robotics company; builds the Apollo robot and runs pilots with Mercedes-Benz, GXO Logistics, and Jabil.
Ouster
United States
San Francisco digital lidar maker founded in 2015; builds the OS0/OS1/OS2/OSDome sensor family and the color-capable REV8 sensor; trades as NYSE: OUST.
KAIST Hubo Lab (Humanoid Robot Research Center)
Korea, Republic of (South)
KAIST humanoid research centre that built HUBO and won the 2015 DARPA Robotics Challenge with DRC-HUBO+; it now develops a 3.25 m/s next-gen humanoid.
Assured Robot Intelligence
United States
San Diego robot-AI start-up founded by Lerrel Pinto and Xiaolong Wang, building humanoid foundation models; acquired by Meta in May 2026.
University of Birmingham — Extreme Robotics Lab (ERL)
United Kingdom
University of Birmingham's Extreme Robotics Lab leads the UK National Centre for Nuclear Robotics; specialises in AI-driven manipulation for nuclear and.
digid GmbH
Germany
German pioneer in nanoscale temperature and force sensor technology for robotics, medical devices, wearables, and industrial applications.
Humanoid M.AX Alliance 휴머노이드 M.AX 얼라이언스
Korea, Republic of (South)
Seoul-based national humanoid robotics consortium launched April 2025 under South Korea's MOTIE, uniting 224 member organizations.
Arcee AI
United States
U.S. AI model lab building efficient open-weight small language and foundation models that run on edge, on-prem or cloud.
Azalea Robotics
United States
Berkeley-based YC-backed startup building fully-mobile collaborative robots for autonomous airport baggage handling on ramps and in terminals.
GMEX Robotics
Australia
Nasdaq-listed robotics company (formerly Fitell) building AI-integrated cobots and autonomous platforms from fitness-hardware roots.
Robotics needs a service framework.
RSF defines a common language for robot service capability, lifecycle operations, certification pathways, and service-provider networks.
Join the RobotToday community on LinkedIn
Daily robotics news, in-depth analysis, conference highlights, and discussions with professionals worldwide.
