A recent analysis of 1,228 vision-language-action papers published between February 2023 and June 2026 found that robot success rates on the Libero benchmark collapse from around 95 percent to below 3…
Google DeepMind introduced Gemini Robotics 2 and Gemini Robotics ER 2, a suite of models that decouple physical control from reasoning for general-purpose robots. The architecture splits tasks across …
Google DeepMind unveiled Gemini Robotics 2, a vision-language-action model that enables whole-body control, advanced dexterity, and multi-robot collaboration, allowing humanoid robots to perform tasks…
Google DeepMind released Gemini Robotics 2, Gemini Robotics ER 2, and Gemini Robotics On-Device 2 on July 30, marking the first vision-language-action model to control a full humanoid end-to-end, demo…
Alphabet Inc.'s Google DeepMind debuted the Gemini Robotics 2 model series for humanoid robots, featuring an embodied reasoning algorithm called Gemini Robotics ER 2 that enables multiple autonomous m…
Apptronik's Apollo 2 humanoid robot demonstrated fine-motor tasks and kitchen chores using Google DeepMind's Gemini Robotics 2 vision-language-action model on July 30, with the system achieving a 68.4…
Google DeepMind released Gemini Robotics 2, a set of three physical AI models for whole-body control, dexterous manipulation, and multi-robot collaboration, moving beyond table-top tasks to full human…
Google DeepMind released Gemini Robotics 2, a family of three models that gives humanoid robots full-body control and enables teamwork, moving beyond tabletop demos to tasks like walking, crouching, a…
Google DeepMind launched Gemini Robotics 2 on July 30, a three-model stack for planning, motor control and local inference across robot bodies including humanoids and dual-arm workstations, with the f…
Google DeepMind introduced Gemini Robotics 2, an AI model that enables whole-body control, fine dexterity, and multi-robot collaboration for humanoid robots. The system includes three models: Gemini R…