Tag
A robotic hand capable of coordinated finger movements, including fist clenching, pointing, and precise pinching, was demonstrated by Xynova at ICRA 2026 in Vienna.
Google DeepMind demonstrates Apollo 2 robot mastering fine motor skills to perform complex kitchen tasks.
Google unveiled Gemini Robotics 2.0, a trio of AI sub-models for robots that improve dexterity, real-time video understanding, and robot collaboration, with the embodied reasoning model publicly available to developers.
DeepMind introduces Gemini Robotics 2, a set of AI models (VLA, ER, On-Device) that enable robots to perform whole-body control, fine dexterity, and multi-robot collaboration, with local on-device execution and fast adaptation to new robot bodies.
1X has developed new 25-DoF robotic hands for its NEO humanoid platform, achieving human-level dexterity, tactile sensing, and durability for real-world manipulation tasks.
MIT researchers developed a wristband with ultrasound stickers that images muscles and tendons, using AI to translate those images into hand movements to wirelessly control a robotic hand with high dexterity.
AGIBOT's humanoid robot flawlessly made a drink, showcasing precise manipulation. The three-year-old company has shipped 5,000 robots this quarter, focusing on perfecting movements before speed.
A proposed benchmark suggests that when robots can economically manufacture clothing, they will be capable of replacing all human labor, as textile work requires high dexterity and low cost.
Google DeepMind introduces Gemini Robotics On-Device, an efficient VLA model optimized to run locally on robotic devices, enabling low-latency operation and offline capability while maintaining strong dexterous manipulation and task generalization. The model can be fine-tuned with as few as 50-100 demonstrations and comes with an SDK for developers.
OpenAI announces Dactyl, a system that learns robotic hand dexterity through simulation and reinforcement learning, using LSTMs to generalize across different physical environments and the Rapid PPO implementation to train policies that transfer to real-world manipulation tasks.
Gemini Robotics 2 demonstrates the ability of robots to perform fine operations (such as packing grapes, screwing in light bulbs, tying knots), reflecting high-precision dexterity.
Gemini Robotics 2 from Google DeepMind demonstrates advanced physical dexterity for robots using different end effectors, enabling more useful robotic capabilities.