Google DeepMind has introduced two advanced artificial intelligence models in its Gemini Robotics family: Gemini Robotics-ER 1.5 and Gemini Robotics 1.5. Designed to power general-purpose robots, these models enhance reasoning, vision, and action capabilities across a range of real-world tasks. The ER 1.5 model acts as the planner, while the 1.5 model executes tasks using natural language instructions.
Two Models for Smarter Robotics
In a blog post, DeepMind explained that these models are aimed at general-purpose robots operating in physical environments. Traditional robotic interfaces often required complex commands, but generative AI allows robots to understand and act on natural language instructions.
Previously, a single AI model handled both planning and execution, leading to errors and delays due to challenges in understanding spatial and temporal dimensions. DeepMind’s solution splits the tasks between two specialized models.
The Gemini Robotics-ER 1.5, a vision-language model, is responsible for planning. It can generate multi-step plans, make logical decisions in physical spaces, and call tools like Google Search to gather information. According to DeepMind, ER 1.5 achieves state-of-the-art performance on spatial understanding benchmarks.
Once the plan is ready, Gemini Robotics 1.5, a vision-language-action model, translates visual input and instructions into motor commands. It calculates the most efficient path to complete tasks and can explain its reasoning in natural language, increasing transparency in robotic actions.
Applications and Availability
This dual-model approach enables robots to execute complex, multi-step tasks seamlessly. For example, a robot could sort objects into compost, recycling, and trash bins by first checking local recycling guidelines, analysing the items, creating a sorting plan, and performing the task.
Google DeepMind also highlighted that the models are adaptable to robots of any shape or size, thanks to their advanced spatial understanding. Currently, the orchestrator model Gemini Robotics-ER 1.5 is available to developers via the Gemini API in Google AI Studio, while the 1.5 model is accessible to select partners.
Also read: Viksit Workforce for a Viksit Bharat
Do Follow: The Mainstream formerly known as CIO News LinkedIn Account | The Mainstream formerly known as CIO News Facebook | The Mainstream formerly known as CIO News Youtube | The Mainstream formerly known as CIO News Twitter |The Mainstream formerly known as CIO News Whatsapp Channel | The Mainstream formerly known as CIO News Instagram
About us:
The Mainstream formerly known as CIO News is a premier platform dedicated to delivering latest news, updates, and insights from the tech industry. With its strong foundation of intellectual property and thought leadership, the platform is well-positioned to stay ahead of the curve and lead conversations about how technology shapes our world. From its early days as CIO News to its rebranding as The Mainstream on November 28, 2024, it has been expanding its global reach, targeting key markets in the Middle East & Africa, ASEAN, the USA, and the UK. The Mainstream is a vision to put technology at the center of every conversation, inspiring professionals and organizations to embrace the future of tech.
