@_philschmid: Bipup beep... Say hello to Gemini Robotics ER 2! ER 2 not only outperforms competing frontier models on embodied reason…
Summary
Gemini Robotics ER 2, built on Gemini 3.5 Flash, was announced with state-of-the-art embodied reasoning, sub-second robot streaming, and multi-robot orchestration support, demonstrated on Boston Dynamics Spot.
View Cached Full Text
Cached at: 07/31/26, 08:49 AM
Bipup beep… Say hello to Gemini Robotics ER 2! ER 2 not only outperforms competing frontier models on embodied reasoning, it thinks and plans next steps simultaneously while executing current actions
- Live API support for bidirectional, sub-second robot streaming.
- 91.3% moment-finding accuracy at 4x faster execution speed.
- 57.4% accuracy tracking 5-stage task progress on video feeds.
- Allows multi-robot orchestration handoffs between different machines.
- Built on Gemini 3.5 Flash (
gemini-robotics-er-2-previewandgemini-robotics-er-2-streaming-preview)
Watching Boston Dynamics Spot complete tasks without awkward freezes feels like a bit step. Excited for the future!
[Video: Boston Dynamics Spot + Gemini Live API]
Similar Articles
Gemini Robotics ER 2: powering robotics with video understanding, task orchestration, and multi-robot collaboration
Google DeepMind launches Gemini Robotics ER 2, an embodied reasoning model that enables robots to understand video, orchestrate tasks, and collaborate with multiple robots, now publicly available via the Gemini API.
Gemini Robotics-ER 1.6: Powering real-world robotics tasks through enhanced embodied reasoning
Google DeepMind introduces Gemini Robotics-ER 1.6, a specialized AI model enhancing embodied reasoning for robotics through improved spatial awareness, task planning, and instrument reading capabilities.
Gemini Robotics brings AI into the physical world
Google DeepMind introduces Gemini Robotics, a Gemini 2.0-based vision-language-action model designed to control physical robots with improved generality, interactivity, and dexterity. The company also launches Gemini Robotics-ER for spatial reasoning and partners with Apptronik to develop humanoid robots.
Gemini Robotics 2 brings whole body intelligence to robots
DeepMind introduces Gemini Robotics 2, a set of AI models (VLA, ER, On-Device) that enable robots to perform whole-body control, fine dexterity, and multi-robot collaboration, with local on-device execution and fast adaptation to new robot bodies.
Gemini Robotics 1.5 brings AI agents into the physical world
Google DeepMind introduces Gemini Robotics 1.5 and Gemini Robotics-ER 1.5, advancing physical AI agents that can perceive, plan, think, and act to complete complex multi-step tasks. Gemini Robotics-ER 1.5 is now available to developers via the Gemini API.