Google has recently launched two innovative artificial intelligence (AI) models, Gemini Robotics and Gemini Robotics-ER, designed to enhance the capabilities of robots in perceiving, interacting with, and operating in the physical world.
These models are built on Google’s Gemini 2.0 AI framework and are expected to improve robots’ ability to perform tasks in various environments, including industrial, commercial, and domestic settings.
The Gemini Robotics model is a vision-language-action (VLA) model that enables robots to understand commands, interpret visual data, and execute physical actions. This means that robots equipped with this model can respond to spoken instructions, recognize objects, and interact with their surroundings more intuitively. The Gemini Robotics-ER model takes this further by incorporating spatial reasoning abilities, allowing robots to understand complex environments and adjust their movements accordingly.
According to Google, these models are designed to be versatile and can be applied to robots of various shapes and sizes, from humanoid robots to industrial machines commonly used in factories and warehouses. The company has already tested Gemini Robotics on its ALOHA 2 bi-arm robotic platform, demonstrating its ability to handle tasks requiring precision and adaptability. Additionally, the model has been successfully applied to Apptronik’s Apollo humanoid robot, which is being developed for real-world applications.
Google’s focus on robotics is a significant move, especially given the recent decision by Figure AI to end its collaboration with OpenAI after making its own innovations in AI-powered robots. With the introduction of Gemini Robotics and Gemini Robotics-ER, Google is poised to make a significant impact on the robotics industry. One of the advantages of these models is their ability to reduce development costs for robotics startups, enabling companies to bring functional robots to market more quickly.
Google has stressed the flexibility of its models, allowing developers to customize them for specific robotic applications using Gemini’s advanced reasoning capabilities. The company has partnered with Apptronik to integrate its AI models into humanoid robots, aiming to create machines capable of performing tasks that require both cognitive reasoning and physical dexterity. This partnership has been supported by a significant funding round, with Google participating to support the development of next-generation humanoid robots.
Google’s move into robotics is not new, having previously acquired Boston Dynamics in 2013 before selling it to SoftBank in 2017. However, the launch of these new AI models marks a renewed push into robotics, with Google focusing on AI-driven intelligence rather than hardware development. By integrating multimodal AI into robotics, Google aims to bridge the gap between digital intelligence and real-world functionality, enabling robots to make work more seamless and efficient.
Read Also: Code With Ease: Google Unveils Free Gemini Code Assist