{"id":"3ccbb952-c7f9-408a-9534-57eb386761a7","slug":"gemini-robotics","name":"Gemini Robotics","description":"Google DeepMind's robotics VLA family. Gemini Robotics builds on Gemini 2.0 with physical actions as an output modality and adds an intermediate reasoning layer for spatial analysis and safety. Gemini Robotics-ER is an embodied-reasoning VLM companion. Gemini Robotics On-Device runs locally, network-independent, and is fine-tunable with 50-100 demonstrations. Gemini Robotics 1.5 introduced 'think before acting'.","brainType":"foundation-model","isOpen":false,"maturityStage":"research","architecture":"VLA built on Gemini 2.0 with physical actions as output modality, plus an intermediate reasoning layer for spatial analysis and safety. Gemini Robotics-ER is the embodied-reasoning VLM companion. Gemini Robotics On-Device runs locally, network-independent, and is fine-tunable with 50-100 demonstrations. Gemini Robotics 1.5 emphasizes a 'think before acting' chain-of-thought style.","reviewStatus":"reviewed","sources":[{"url":"https://deepmind.google/models/gemini-robotics","label":"Google DeepMind: Gemini Robotics (primary)"},{"url":"https://deepmind.google/blog/","label":"Google DeepMind Blog"},{"url":"https://deepmind.google/blog/gemini-robotics-brings-ai-into-the-physical-world/","title":"Gemini Robotics brings AI into the physical world (VLA on Gemini 2.0 + Gemini Robotics-ER)","mediaType":"article","sourceName":"Google DeepMind"},{"url":"https://deepmind.google/blog/gemini-robotics-on-device-brings-ai-to-local-robotic-devices/","title":"Gemini Robotics On-Device brings AI to local robotic devices (Apollo, Franka FR3)","mediaType":"article","sourceName":"Google DeepMind"},{"url":"https://deepmind.google/blog/gemini-robotics-15-brings-ai-agents-into-the-physical-world/","title":"Gemini Robotics 1.5 brings AI agents into the physical world (thinking VLA + ER 1.5)","mediaType":"article","sourceName":"Google DeepMind"},{"url":"https://deepmind.google/models/gemini-robotics/","title":"Gemini Robotics (canonical model family landing page)","mediaType":"article","sourceName":"Google DeepMind"},{"url":"https://arxiv.org/abs/2503.20020","title":"Gemini Robotics: Bringing AI into the Physical World (technical report)","mediaType":"article","sourceName":"arXiv (Google DeepMind)"},{"url":"https://www.therobotreport.com/google-deepmind-introduces-on-device-gemini-ai-model-robots/","title":"Google DeepMind introduces on-device Gemini AI model for robots","mediaType":"article","sourceName":"The Robot Report"}],"keyFacts":[{"label":"DEPLOY maturity rationale","value":"Most advanced DeepMind VLA; commercializing via Apptronik; not at-scale production. Re-derived as research-to-commercial; recorded here as research given current scale"},{"label":"Announced","value":"March 2025"},{"label":"Apptronik partnership","value":"Confirmed; Gemini Robotics powers Apptronik Apollo in joint roadmap"},{"label":"On-Device variant","value":"First DeepMind VLA available for fine-tuning; 50-100 demonstrations"},{"label":"Cross-embodiment","value":"Trusted-tester robots; cross-platform deployment"},{"label":"Apollo partnership type","value":"The Apollo (Apptronik) relationship is investment-linked: Google led Apptronik's Series A and the Gemini Robotics partnership formalizes the technology integration. Distinct from Atlas-Gemini, which is a dedicated bidirectional co-development with Boston Dynamics. Apollo also operates inside NVIDIA's Isaac ecosystem; primary-source evidence for GR00T as Apollo's onboard brain at runtime is not yet established, so DEPLOY does not record a GR00T powers relation on Apollo (only the Gemini Robotics powers relation)."},{"label":"wikidata","value":"https://www.wikidata.org/wiki/Q133568202"},{"label":"wikipedia","value":"https://en.wikipedia.org/wiki/Gemini_Robotics"}],"aliases":["Gemini Robotics","Gemini Robotics-ER","Gemini Robotics On-Device","Gemini Robotics 1.5","Gemini Robotics ER 1.6"],"collisionRisk":"low","reviewNote":null,"builtOnBrainId":null,"createdAt":"2026-05-28T14:06:07.926Z","updatedAt":"2026-06-03T22:14:53.088Z","jsonLd":{"@context":"https://schema.org","@type":"SoftwareApplication","@id":"https://registry.deploy.report/brains/gemini-robotics","url":"https://registry.deploy.report/brains/gemini-robotics","name":"Gemini Robotics","alternateName":["Gemini Robotics","Gemini Robotics-ER","Gemini Robotics On-Device","Gemini Robotics 1.5","Gemini Robotics ER 1.6"],"description":"Google DeepMind's robotics VLA family. Gemini Robotics builds on Gemini 2.0 with physical actions as an output modality and adds an intermediate reasoning layer for spatial analysis and safety. Gemini Robotics-ER is an embodied-reasoning VLM companion. Gemini Robotics On-Device runs locally, network-independent, and is fine-tunable with 50-100 demonstrations. Gemini Robotics 1.5 introduced 'think before acting'.","identifier":["3ccbb952-c7f9-408a-9534-57eb386761a7",{"@type":"PropertyValue","propertyID":"wikidata","value":"Q133568202"}],"applicationCategory":"foundation-model","sameAs":["https://www.wikidata.org/wiki/Q133568202","https://en.wikipedia.org/wiki/Gemini_Robotics"],"publisher":{"@id":"https://deploy.report/#organization"}},"framework_metadata":{"framework_schema_version":"0.1.0","verification_status":"verified","maturity_stage":"research","lifecycle_state":null,"architectural_position":{"cohort":null,"sub_cohorts":[]},"within_cohort_verified_vs_claimed_pair":null,"cap_flags":[],"verification_depth":{"sources_count":8,"primary_source_types":["preprint","secondary-trade-publication"]}}}