Gemini Robotics ER 2: Powering Robotics with Video Understanding, Task Orchestration, and Multi-Robot Collaboration
Gemini Robotics ER 2: powering robotics with video understanding, task orchestration, and multi-robot collaboration
Google DeepMind has launched Gemini Robotics ER 2, a new model that enhances robotics through video understanding, task orchestration, and multi-robot collaboration. It enables robots to perform complex tasks, adapt in real-time, and work together in shared environments. The model also improves safety and spatial reasoning capabilities, with performance benchmarks showing significant gains over previous versions.
Google DeepMind's Gemini Robotics ER 2 introduces a significant advancement in embodied reasoning for robotics, integrating video understanding, task orchestration, and multi-robot collaboration. It outperforms its predecessor in tool orchestration and safety benchmarks, enabling more robust and adaptive physical AI systems.
Evidence and limits
Published automatically after robotics and source-evidence checks; no manual editorial approval is recorded. Source assertions are not independently verified. Missing information remains not reported.
- Environment:
- Not reported
- Control:
- Not reported
- Data origin:
- Not reported
Source excerpts and review record
No manual editorial approval recorded.
Original source quotation: “Gemini Robotics ER 2 represents a step change in powering robots with video understanding, task orchestration, and multi-robot collaboration — making it possible for robots to be more helpful in the physical world.”
Source E1
Original source quotation: “Gemini Robotics ER 2 can also natively call tools like Google Search to find information, or any other user-defined function.”
Source E2
Original source quotation: “Gemini Robotics ER 2 consistently outperforms ER 1.6 for tool orchestration across three control modes: real VLA, sim VLA, and human tele-op.”
Source E3
Original source quotation: “Gemini Robotics ER 2 achieves 57.4% accuracy on progress classification tasks, outperforming previous generation models and competing frontier models.”
Source E4
Original source quotation: “Gemini Robotics ER 2 achieves 91.3% accuracy and a 0.96s mean absolute distance.”
Source E5
Original source quotation: “Gemini Robotics ER 2 outperforms ER 1.6 and other frontier models on Safety Instruction Following and Human Proximity benchmarks.”
Source E6
Source：Google DeepMind — Robotics · deepmind.google