Google New Gemini Robotics Model Robot AI Real World
Google Deepmind’s new Gemini Robotics model, built on Gemini 2.0, is the most advanced yet, as it helps a variety of robots to perform a wider range of real-world tasks than ever before.



Gemini Robotics employs the model’s world understanding to generalize to novel situations and solve a wide variety of tasks straight out of the box, including ones it has never tackled before in training. It can also deal with new objects, diverse instructions, and new environments, all the while continuously monitoring its surroundings, detecting changes to its environment or instructions, as well as adjust its actions accordingly. Dexterity has been vastly improved, which means robots can now handle extremely complex, multi-step tasks that require precise manipulation like origami folding or packing a snack into a zippered bag.

Sale

LEGO Icons Optimus Prime 10302 Transformers Figure Set, Collectible Transforming 2-in-1 Robot and Truck...

LEGO Icons Optimus Prime 10302 Transformers Figure Set, Collectible Transforming 2-in-1 Robot and Truck…

  • With this set, based on the legendary Transformers Autobot, adults build LEGO Optimus Prime figure that converts from robot to truck and back
  • Relive the Transformers saga with accessories, including the ion blaster, Autobot Matrix of Leadership, an Energon axe, Energon cube and jetpack
  • This unique collectible robot model makes a great home décor piece – top off the build with a unique display plaque with Optimus Prime facts

Alongside Gemini Robotics, we’re introducing an advanced vision-language model called Gemini Robotics-ER (short for ‘“embodied reasoning”). This model enhances Gemini’s understanding of the world in ways necessary for robotics, focusing especially on spatial reasoning, and allows roboticists to connect it with their existing low level controllers,” said Carolina Parada, Senior Director and Head of Robotics at Google DeepMind.

[Source]