Google DeepMind Unveils Gemini Robotics 2 AI Model for Humanoid Robots
- Published
- Source
- RobotStart.info
On July 30, 2026, Google DeepMind announced the latest AI model for humanoid robots, Gemini Robotics 2. This model advances from upper-body control to full-body control, enabling walking, bending, and advanced dexterity, as well as collaborative tasks among multiple robots.
Gemini Robotics 2 translates visual and language inputs into motion control, supporting full-body and dual-arm robot operations. It features enhanced physical reasoning capabilities with Gemini Robotics ER 2, which manages human communication and multi-step task planning, and Gemini Robotics On-Device 2, which adapts quickly to new robots with minimal data.
The model demonstrated its capabilities using Apptronik's humanoid robot Apollo 2, performing tasks such as walking to a table, lifting objects, and accurately storing them. With a 22-degree-of-freedom hand, it can execute delicate tasks like tying knots. The introduction of the ASIMOV-Agentic benchmark emphasizes safety, allowing the robot to detect human presence and stop safely, marking it as the safest model to date.
Original report
Google DeepMind、ヒューマノイド向けAIモデル「Gemini Robotics 2」発表 全身制御と高度な器用さを実現
RobotStart.infoThis 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
RobotToday Weekly October 12 – 16, 2026 RobotToday · 1 week ago
- 11
-
12
automatica 2027 – Munich, Jun 22–25, 2027 RobotToday · 2 weeks ago
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.
Apptronik
United States
Austin, Texas humanoid robotics company; builds the Apollo robot and runs pilots with Mercedes-Benz, GXO Logistics, and Jabil.
TRON K.K.
Japan
Tokyo humanoid integrator (est. 2024) bringing physical-AI robots, simulation training and Prevu3D factory digital twins to Japanese manufacturers.
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.
Tangible Robots
United States
San Francisco startup building Eggie, a wheeled humanoid with humanlike hands for household dexterity tasks, backed by Blume Ventures and Micelio.
Techsoft Robots 深圳市泰科智能机器人有限公司
China
Shenzhen manufacturer of humanoid and collaborative robot joint modules, servo drives, and dual-arm cobots for OEM and end-user customers.
Liquid AI
United States
MIT-spinout building device-native foundation models (LFMs) that run on-device across phones, cars, robots and edge hardware.
Aether AI
United States
Seed-stage San Diego startup building causal world models that predict action outcomes, with robotics as its first target market.
Voxel AI
United States
US-based AI company offering a computer vision site intelligence platform that converts existing security cameras into real-time workplace safety monitoring.
ITURRI
Spain
Spanish industrial group (est. 1947, Seville) offering passive and active exoskeletons under exoITURRI brand to reduce musculoskeletal disorders for workers.
TRACLabs, Inc.
United States
NASA-partnered robotics software company specializing in human-robot interfaces, electronic procedures, and autonomous task planning.
Thinking Robots Inc.
United States
Developer of AI software enabling robots to be instructed in natural language without programming or prior training, with on-the-fly learning and task.
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.
