Audience
Industrial robotics developers building adaptable humanoid and multi-robot systems for complex physical environments
About Gemini Robotics 2
Gemini Robotics 2 is Google DeepMind’s intelligence layer for adaptable robots, bringing whole-body control, advanced dexterity, embodied reasoning, and multi-robot collaboration to physical AI. It includes three models. Gemini Robotics 2 is a vision-language-action model that converts visual and language input into motor control, enabling humanoids and bi-arm robots to act from feet to fingertips. It can coordinate walking, crouching, reaching, balancing, and object manipulation, while controlling five-fingered hands or standard grippers for delicate and precise tasks. Gemini Robotics ER 2 serves as the high-level brain, communicating with people, understanding its surroundings, planning multi-step tasks that last several minutes, coordinating actions with the VLA, tracking progress, self-correcting failures, and allowing different robots to work together.
Other Popular Alternatives & Related Software
CloudMinds
To operate smart robots for people, currently we build and operate an open end-to-end cloud robot system, and offer it as a service to the world. Our pioneering world-class architecture connects robots and smart devices over a secure Virtual Backbone Networks (VBNs) to Cloud AI. Our Human Augmented Robotics Intelligence with Extreme Reality (HARIX) platform is an ever evolving “cloud brain” capable of operating millions of cloud AI robots performing different tasks simultaneously. Complemented by our smart joint technology (SCA), our cloud AI capabilities include Natural Language Processing (NLP), Computer Vision (CV), navigation, and vision-controlled manipulation that’s bringing a vibrant cloud ecosystem of next generation robotics and smart devices to many industry value chains.
Learn more
Gemini Robotics-ER 1.6
Gemini Robotics-ER 1.6 is a family of AI models developed by Google DeepMind to bring advanced multimodal intelligence into the physical world by enabling robots to perceive, reason, and act in real-world environments. Built on the Gemini 2.0 foundation, it extends traditional AI capabilities by adding physical action as an output modality, allowing robots to interpret visual input and natural language instructions and convert them directly into motor commands to complete tasks. It includes a vision-language-action model that processes images and instructions to execute tasks, as well as a complementary embodied reasoning model (Gemini Robotics-ER) that specializes in spatial understanding, planning, and decision-making within physical environments. These models enable robots to generalize across new situations, objects, and environments, allowing them to perform complex, multi-step tasks even if they were not explicitly trained for them.
Learn more
Gemini Robotics
Gemini Robotics brings Gemini’s capacity for multimodal reasoning and world understanding into the physical world, allowing robots of any shape and size to perform a wide range of real-world tasks. Built on Gemini 2.0, it augments advanced vision-language-action models with the ability to reason about physical spaces, generalize to novel situations, including unseen objects, diverse instructions, and new environments, and understand and respond to everyday conversational commands while adapting to sudden changes in instructions or surroundings without further input. Its dexterity module enables complex tasks requiring fine motor skills and precise manipulation, such as folding origami, packing lunch boxes, or preparing salads, and it supports multiple embodiments, from bi-arm platforms like ALOHA 2 to humanoid robots such as Apptronik’s Apollo. It is optimized for local execution and has an SDK for seamless adaptation to new tasks and environments.
Learn more
NVIDIA Isaac
NVIDIA Isaac is an AI robot development platform that comprises NVIDIA CUDA-accelerated libraries, application frameworks, and AI models to expedite the creation of AI robots, including autonomous mobile robots, robotic arms, and humanoids. The platform features NVIDIA Isaac ROS, a collection of CUDA-accelerated computing packages and AI models built on the open source ROS 2 framework, designed to streamline the development of advanced AI robotics applications. Isaac Manipulator, built on Isaac ROS, enables the development of AI-powered robotic arms that can seamlessly perceive, understand, and interact with their environments. Isaac Perceptor facilitates the rapid development of advanced AMRs capable of operating in unstructured environments like warehouses or factories. For humanoid robotics, NVIDIA Isaac GR00T serves as a research initiative and development platform for general-purpose robot foundation models and data pipelines.
Learn more
Integrations
Company Information
Google DeepMind
Founded: 2010
United Kingdom
deepmind.google/blog/gemini-robotics-2-brings-whole-body-intelligence-to-robots/
Videos and Screen Captures
Other Useful Business Software
$300 Free Credits to Build on Google Cloud
Put your $300 in credit toward real workloads, then keep building with free monthly usage for 20+ products. No commitment and no charge until you upgrade.
Product Details
Platforms Supported
Cloud
Training
Documentation
Videos
Support
Online
