DeepMind Unveils Gemini Robotics 1.5 for Advanced AI-Driven Robotics

Sep 25, 2025
DeepMind has introduced Gemini Robotics 1.5, a new AI model designed to enhance robotic capabilities by integrating vision, language, and action. The model is available to select partners, while Gemini Robotics-ER 1.5 is accessible via the Gemini API in Google AI Studio.

DeepMind has introduced Gemini Robotics 1.5, a new AI model designed to bring advanced capabilities to robots by integrating vision, language, and action. announced on their website, this model allows robots to convert visual information and instructions into motor commands, enabling them to perform complex tasks with greater transparency and efficiency.

The Gemini Robotics-ER 1.5 model, also introduced, focuses on reasoning about the physical world and creating detailed, multi-step plans. It achieves state-of-the-art performance in spatial understanding benchmarks and is now available to developers via the Gemini API in Google AI Studio. Meanwhile, Gemini Robotics 1.5 is currently accessible to select partners.

These models are part of DeepMind's efforts to advance intelligent, general-purpose robots capable of understanding and interacting with their environment to complete complex tasks. The models are built on the core Gemini family and have been fine-tuned to specialize in their respective roles, enhancing the ability of robots to generalize across diverse environments and tasks.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like Robotics Brief or Daily AI Brief.

Also, consider following us on social media:

AI & Robotics AI Brief AI Brief (X)
Free newsletter

Robotics Brief

Weekly coverage of AI-driven robotics advances in industrial automation, autonomous vehicles, and robotic systems.

AI Token Webinar

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more

You may also like

Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.