media MarkTechPost · 2h ago · releases

Google DeepMind releases Gemini Robotics 2 for whole body control and dexterity

from English

Google DeepMind has released Gemini Robotics 2, an intelligence layer comprising three models designed to enable whole-body control, five-finger dexterity, and multi-robot collaboration. The release includes a Vision-Language-Action (VLA) model, an embodied reasoning VLM, and an on-device VLA, moving beyond previous table-top manipulation capabilities.

Gemini Robotics 2 VLA drives full humanoids like Apptronik Apollo 2 with SharpaWave hands, achieving success rates ranging from 32% to 92% across dexterity tasks.
Gemini Robotics ER 2, based on Gemini 3.5 Flash, handles high-level planning and tool orchestration with a 128k context window and bidirectional streaming via the Gemini Live API.
Gemini Robotics On-Device 2 allows local execution and rapid adaptation to new robot bodies, such as the SO101 platform, where performance jumped from 6.7% to 53.3% success.
The suite supports multi-robot collaboration, demonstrated by pairing Apollo 2 with a Franka F3 Duo for shared semantic task handoffs.

The models aim to address the limitations of pre-programmed robots by enabling adaptation to unpredictable environments and skill transfer across different robot bodies.

Importance 3/3 New feature vs. leaders MarkTechPost Google DeepMind AI agents Robotics

Related articles

lab Google DeepMind Blog · 8h ago · 3 views

Google introduces Gemini Robotics 2 for whole-body control and multi-robot collaboration

Google has introduced Gemini Robotics 2, an intelligence layer designed to provide adaptable robots with intelligent whole-body control, advanced dexterity, and the ability to collaborate in teams. This update expands physical AI capabilities beyond narrow, repetitive tasks by enabling robots to reason through movements and adapt to new bodies quickly.

lab Google DeepMind Blog · 9h ago · 9 views

Google launches Gemini Robotics ER 2 with video understanding and multi-robot collaboration

Google has launched Gemini Robotics ER 2, a new embodied reasoning model designed to help robots think fast and plan multi-step tasks in real-time. The update introduces significant upgrades over the previous ER 1.6 version, including continuous video-based progress tracking, precision moment-finding, and native multi-robot collaboration capabilities.

arxiv arXiv cs.AI · 42d ago · 1 view

Finetuning VLA Models Requires Fewer Layers Than Thought

Vision-Language-Action models show severe layer-wise redundancy despite large parameter counts. A training-free compression method using Centered Kernel Alignment removes twin layers, reducing model depth by up to 50% and enabling 40-50% faster training and up to 30% faster inference without performance loss, validated across simulation and real-world robotic tasks.

arxiv arXiv cs.LG · 45d ago · 2 views

ROVE: Reinforcement Learning with Human Interventions for Humanoid Manipulation

ROVE enables humanoid Vision-Language-Action models to learn effective manipulation behaviors using imperfect human interventions. It combines a human-in-the-loop data collection pipeline with Optimistic Value Estimation and cross-embodiment supervision to prioritize high-value actions and improve robustness. ROVE outperforms baseline methods on real-world, contact-rich manipulation tasks through iterative rollout and intervention cycles.

lab Google — The Keyword (AI) · 2d ago · 5 views

Gemini API Managed Agents adds hooks, model selection, and free tier

Google has updated the Gemini Interactions API's Managed Agents to include environment hooks, explicit model selection, and free tier access. These capabilities build on previous releases introducing background tasks and remote MCP server integration.