Zip Robotic

Category: Humanoids

Humanoid robots are the most watched and least proven category in robotics. This is where we track the machines built in roughly human shape — Atlas, Digit, Optimus, Figure, UBTECH’s Walker line and the fast-moving Chinese challengers — and, more importantly, what they are actually being asked to do. Most humanoid deployments today are parts logistics, sequencing and tote handling: repetitive work that demands two hands and awkward grasps but never touches a moving assembly line. The gap between that and full component assembly is where the real engineering story lives. We report the specifics — payload, runtime, charge ratio, unit counts, factory capacity, order books — and we flag the difference between a stated production target and a robot doing paid work. Expect coverage of training methods (teleoperation, reinforcement learning in simulation, human demonstration capture), the data-flywheel claims every programme now makes, and the throughput question almost nobody answers: how many hours of demonstration produce one reliably autonomous task.

  • DeepMind’s Gemini Robotics 2 Brings Whole-Body Control to Humanoids

    DeepMind’s Gemini Robotics 2 Brings Whole-Body Control to Humanoids

    Google DeepMind has released Gemini Robotics 2, a family of three models that gives robots whole-body control, multi-minute task planning and the ability to coordinate with other robots. It’s the most significant update to Google’s robot “brain” since the original Gemini Robotics launched, and it lands as every humanoid company on earth is racing to build or buy exactly this kind of model.

    The three models

    • Gemini Robotics 2 (VLA) — the vision-language-action model that turns instructions and camera input into motor commands. Early access.
    • Gemini Robotics-ER 2 — the embodied-reasoning model for planning and spatial understanding. Available now in Google AI Studio.
    • On-device variant — runs locally on the robot for low-latency control. Early access.

    Demos ran on Apptronik’s Apollo 2 humanoid, Franka’s Duo gripper and Sharpa Wave dexterous hands, and DeepMind says the models can adapt to a new robot body in hours rather than weeks. Reported success rates included 76.3% on a shelf-pickup task, 89.6% on insertion and 92% on unscrewing light bulbs.

    Safety as a benchmark

    Alongside the models, DeepMind introduced ASIMOV-Agentic, a safety benchmark for agentic robots. In demonstrations, robots refused commands judged unsafe and asked a human for help when uncertain — behavior that will matter enormously once these systems are operating around people rather than in labs.

    Sources