Explore Gemini Robotics-ER 1.5
Our Gemini-based multimodal model gives advanced world understanding to robots.
For example, let’s say a human instructed it to ‘clean the kitchen’. The ER model would break down the task into smaller, manageable steps – clear the counter, load the dishwasher, wipe the surfaces. This model also supports thinking.
Orchestrates robot activities, like a high-level brain. Excels at planning and making logical decisions within a physical environment. Interacts in natural language, estimates progress, and can natively call tools – like using Google Search to look for information.
Perceives and understands the surrounding environment to locate and handle objects with greater accuracy.
Understands the cause and effect relationships between objects and actions as they unfold over time.
Aggregated performance on 15 embodied reasoning academic benchmarks. The benchmarks include: Point-Bench, RefSpatial, RoboSpatial-Pointing, Where2Place, BLINK, CV-Bench, ERQA, EmbSpatial, MindCube, RoboSpatial-VQA, SAT, Cosmos-Reason1, Min Video Pairs, OpenEQA and VSI-Bench.
