VLA models
Gemini Robotics 1.5 (+ Gemini Robotics-ER 1.5)
United States
Google DeepMind's agentic robotics stack: ER 1.5 plans, reasons spatially and calls tools (available via the Gemini API; ER 1.6 followed in 2026), while the Gemini Robotics 1.5 VLA executes and transfers motions across embodiments. Model weights remain closed, with the VLA limited to selected partners.
OrganizationGoogle DeepMind
CountryUS
Release2025-09
Open weightsno
Architecturedual-model agentic system: Gemini Robotics-ER 1.5 (embodied-reasoning orchestrator with tool calling) + Gemini Robotics 1.5 VLA executor with motion transfer and interleaved natural-language thinking
Modalitiesvision, language, action
Embodimentsmanipulator, humanoid, cross-embodiment
Training dataNot disclosed in detail; multi-embodiment robot data across ALOHA 2, bi-arm Franka and Apptronik Apollo, leveraged via a Motion Transfer mechanism on top of Gemini multimodal pretraining
Sources : Google DeepMind (2025-09-25)arXiv (2025-10-03)Google AI for Developers (2026-07-09)
← Back to comparator · VLA models