Google’s latest AI update makes industrial robots smarter — here’s how

Google DeepMind Introducing Gemini Robotics-ER 1.6 On Tuesday, an artificial intelligence model was developed designed to enable robots to perform complex real-world tasks through enhanced embodied thinking capabilities. The model specializes in spatial understanding, task planning and success detection, representing a major advance in AI-powered robotics that could accelerate enterprise adoption of autonomous systems.

The new model shows measurable improvements over its predecessor and Gemini 3.0 Flash on spatial and physical reasoning tasks. Gemini Robotics-ER 1.6 can read complex measuring devices and vision goggles, a capability developed by Google DeepMind through a collaboration with Boston Dynamics to address specific industrial needs.

In safety hazard identification tests, the model showed a 6% improvement in text-based scenarios and a 10% improvement in video-based scenarios compared to Gemini 3.0 Flash. Enhanced capabilities are now available to developers through the Gemini API and Google AI Studio.

Deployment of the model in the real world is already underway. Boston Dynamics Gemini and Gemini Robotics ER 1.6 integrated in its Orbit AIVI-Learning system, with the transition for registered customers starting on April 8.

“Capabilities such as instrument reading and more reliable mission reasoning will enable Spot to see, understand and react to real-world challenges completely autonomously,” said Marco da Silva, Spot’s vice president and general manager at Boston Dynamics.

This collaboration signals a shift from experimental AI research towards practical industrial applications. Enhanced spatial reasoning and tool-reading capabilities could enable robots to perform maintenance, inspection and monitoring tasks that previously required human supervision.

Google noted that the collaboration strengthens Boston Dynamics’ established presence in commercial robotics, where Spot robots already navigate construction sites and industrial facilities. Integrating advanced AI into proven hardware platforms represents a convergence that can accelerate autonomous system deployment across industries.

Decryption He covered Google’s evolving capabilities in AI-powered robotics, including the company’s previous development of robots that He can think and search the webas well as Boston Dynamics Atlas trading robot with human appearance advertisement.