Responsibly advancing AI and robotics We’re developing a broad and rigorous safety framework so Gemini-controlled robots can be used responsibly in real-life environments We use multiple layers of semantic, physical, and operational safeguards to reduce and mitigate risks – an approach based on in-depth research. Our safety framework in detail Think of our safety framework as a stack of Swiss cheese slices. No single slice is a perfect barrier. But together, they help prevent accidents. Human-robot interactionWe’ve implemented safeguards to improve the way our models behave in social settings – in what they say, their gestures, and their actions. This falls in line with our Gemini safety policies. Semantic safetyIt’s important these models have what a human would call ‘common sense’. For example, they mustn’t hand a boiling drink to a young child, or pass a very heavy box to a human. We’ve released new datasets and benchmarks to help us evaluate and improve semantic safety. Physical safetyOur VLA models can be composed with lower-level safety mechanisms to help prevent accidents. And we’re implementing best practices for safe data collection and evaluation. Assessing vulnerabilitiesWe’ve created systems that continuously search for vulnerabilities within our robotics models. By uncovering potential gaps, we can respond with further improvements. Read the Gemini Robotics 1.5 tech report for more details on our scalable adversarial evaluations. Thinking improves safety The ability to think through real-world risks helps Gemini Robotics 1.5 act appropriately while interacting with humans, while making its decisions more transparent in natural language. Here are a few examples of how it makes safe decisions in real-world environments. Assessing risks in interactionsWhile interacting with objects, the models are designed to use logic to decide whether an action is appropriate and safe. For example, assessing an item’s weight to decide if it’s possible to lift. Environmental risksThe models can identify risks within the physical surroundings, and in videos they are told to watch. For example, if they see a person potentially being exposed to an electric shock, they can assess and identify that risk. Responding to safety distancesThe models are able to detect humans entering their operating area. If this happens, they are designed to stop work to help keep people safe from accidental harm. This is part of our ongoing research – this feature is not a guaranteed safety-rated system. Pause video Play video Related publications Our research team has produced a number of key papers that have informed our rigorous approach to safety. Generating Robot Constitutions & Benchmarks for Semantic Safety Predictive Red Teaming: Breaking Policies Without Breaking Robots SciFi-Benchmark: How Would AI-Powered Robots Behave in Science Fiction Literature? 2024 Best RoboCup Paper AwardEmbodied AI with Two Arms: Zero-shot Learning, Safety and Modularity Safely Learning Dynamical Systems Finalist for Best Planning Paper AwardOptimizing Trajectories with Closed-loop Dynamic SQP Learning Model Predictive Controllers with Real-Time Attention for Real-World Navigation Experience Gemini Robotics If you're interested in testing our models, please share a few details to join the waitlist. Bear in mind that we haven’t tested them across every make or model of robot. It’s your responsibility to use our models (and any equipment) safely and appropriately. Join the trusted tester waitlist