Gemini Robotics 2
Gemini Robotics 2 is Google DeepMind’s intelligence layer for adaptable robots, bringing whole-body control, advanced dexterity, embodied reasoning, and multi-robot collaboration to physical AI. It includes three models. Gemini Robotics 2 is a vision-language-action model that converts visual and language input into motor control, enabling humanoids and bi-arm robots to act from feet to fingertips. It can coordinate walking, crouching, reaching, balancing, and object manipulation, while controlling five-fingered hands or standard grippers for delicate and precise tasks. Gemini Robotics ER 2 serves as the high-level brain, communicating with people, understanding its surroundings, planning multi-step tasks that last several minutes, coordinating actions with the VLA, tracking progress, self-correcting failures, and allowing different robots to work together.
Learn more
FLUX 3 Action
FLUX 3 Action is an open-weight 7B world-action model designed for action prediction in robotics and other latency-sensitive visual environments. Derived from the multimodal FLUX 3 backbone, it was pretrained on large-scale image, video, and audio data with a strong emphasis on video, then adapted through joint video-action training and fine-tuning for specific embodiments and action spaces. Given an instruction, camera observations, and robot joint positions, the model predicts motor commands together with their expected visual outcomes, allowing a robot to execute actions, observe the environment again, and continuously replan. Unlike approaches that separate visual prediction from control, FLUX 3 Action jointly models future video and actions, transferring world understanding learned from broad video pretraining into robot control. Its single-step 7B checkpoint reaches a 38.3% success rate on RoboLab-120.
Learn more
MaestroAR
MaestroAR® provides procedure-specific learning in 3D augmented reality on both dV-Trainer® and FlexVR™ robotic surgery simulators. Based on recorded surgical procedures, MaestroAR® allows trainees to immerse themselves in the surgery by using the simulator to control virtual robotic instruments to interact with anatomical regions within the augmented 3D video. Maestro AR® provides opportunities to gain procedural familiarity and to develop decision-making skills. Narrated by influential, globally-recognized robotic surgeon educators, the trainee is guided through a complete robot-assisted surgical procedure, step by step. The trainee manipulates virtual 3D robotic instruments in order to answer questions about the procedure, identify and interact with anatomical regions, and perform virtual reality skills exercises.
Learn more
RobotStudio
RobotStudio is the world’s most popular offline programming and simulation tool for robotic applications. Based on the best-in-class virtual controller technology, the RobotStudio suite gives you full confidence that what you see on your screen matches how the robot will move in real life. Enabling you to build, test, and refine your robot installation in a virtual environment, this unique technology speeds up commissioning time and productivity by a magnitude. The RobotStudio desktop version allows you to carry out programming and simulation without disturbing ongoing production. RobotStudio cloud enables individuals and teams to collaborate in real-time on robot cell designs from anywhere in the world, on any device. The RobotStudio Augmented Reality Viewer enables you to visualize robots and solutions in a real environment or in a virtual room on any mobile device for free. Both the desktop and mobile applications enable teams to collaborate and make faster decisions.
Learn more