Gemini Robotics 2 reaches whole-body control
Google DeepMind expanded its robotics model from upper-body tasks to coordinated locomotion, posture changes and manipulation across embodiments.
Event Type: model release
Embodied reasoning becomes task orchestration
ER 2 adds video understanding, multi-step planning, progress checking and higher-level orchestration above lower-level robot control.
On-device adaptation reduces cloud dependence
The local model targets rapid adaptation to new robot bodies and objects using fewer than two hundred examples.
Multi-robot collaboration enters the model stack
The updated model family supports multiple robots coordinating in shared spaces rather than treating each machine as an isolated agent.
Gemini Moves From Manipulation to Whole-Body Control
Gemini Robotics 2 reporting extends control toward locomotion, dexterity and coordinated whole-body tasks.
Embodied Reasoning Expands to Longer Tasks
Google separated higher-level planning from physical control while broadening multi-step task execution.
Gemini Robotics 2 Reaches Whole-Body Control
Gemini Robotics 2 extends control toward walking, crouching, dexterous manipulation and coordinated whole-body tasks.
Embodied Reasoning Expands to Longer Tasks
Google broadened dexterity, multi-step execution and the separation of higher-level planning from physical control.
On-Device Adaptation Broadens Robot Portability
The on-device model was reported to adapt rapidly across robots with differing sensors and embodiments.
Google DeepMind releases Gemini Robotics 2
Gemini Robotics 2 expands robot planning, dexterity, and full-body control across humanoid and task-oriented platforms.
