Humanoid Robotics Technology

Unitree Robotics has unveiled a preview of its new robot. After just over three months of development, it has achieved a standing high jump of 2 m and a top speed of 12.66 m/s, with a leg length of just 0.85 m. Discover more about the humanoid industry here: https://lnkd.in/eNdkY_-f #humanoids #humanoidrobotics #humanoidrobot #humanoid

Check out this video from Phybot Technology showcasing its humanoid robots playing football, demonstrating their ability to navigate dynamic environments. Curious about the humanoid industry? Learn more: https://lnkd.in/eNdkY_-f #humanoids #humanoidrobotics #humanoid #humanoidrobot

LG Electronics has announced it’s developing a next-generation bipedal humanoid robot built using NVIDIA Isaac GR00T. Expected to be unveiled in Q1 next year, the robot will leverage NVIDIA's open reasoning humanoid foundation model. “Building on years of collaboration, LG and NVIDIA are combining LG’s leadership in product engineering and manufacturing with NVIDIA technology to accelerate the next era of robots, AI factories and autonomous vehicles,” said Jensen Huang, founder and CEO of NVIDIA. Learn more: https://lnkd.in/evNfzVFP #humanoids #humanoidrobot #humanoid #humanoidrobotics

CoorDex is a learning pipeline for continuous dexterous humanoid loco-manipulation. Starting from simulated whole-body and hand demonstrations, CoorDex trains privileged motion-tracking teachers for the humanoid body and dexterous hands, distills them into proprioception-conditioned latent priors, and uses these frozen priors as the action space for downstream residual reinforcement learning. Read the paper here: https://lnkd.in/ewhkAu2C  #humanoids #humanoidrobotics #humanoid #humanoidrobot The University of North Carolina at Chapel Hill, University of California, Berkeley

Micro-Measurements designs custom strain gage-based sensing solutions engineered for the exact space, load, and performance requirements of humanoid robots. Their sensing technology enables precise force and tactile feedback, supporting realistic touch and interaction in robotics. Discover more about Micro-Measurements here: https://lnkd.in/e5zQ2quW #humanoids #humanoidrobotics #humanoid #humanoidrobot

Sarcomere Dynamics' TALOS Hand delivers impressive dexterity for industrial pick and place, bin picking, and autonomous sorting. This video demonstrates the TALOS Hand’s strength, powered by Sarcomere Dynamics’ brushless actuator technology. Features:  ☑️ Degrees of freedom: 10 ☑️ Weight: 650 g  ☑️ Nominal voltage, power: 24 V, 40 W  ☑️ Cycling speed: 1.1 Hz Get more information about the TALOS Hand here: https://lnkd.in/ejSiHFrm #humanoid #humanoids #humanoidrobot #humanoidrobotics

Without reliable sensors, robotic systems would lack the feedback needed for intelligent behaviour. XJCSENSOR develops advanced sensing technologies that help humanoid robots operate with greater accuracy, safety, and efficiency. From force and torque sensors to load and multi-axis sensing solutions, their technology provides the feedback robots need to perform complex tasks with precision. Learn more about XJCSENSOR's sensor solutions here: https://lnkd.in/ebEVrGxx #humanoids #humanoidrobotics #humanoidrobot #humanoid

Dobot Robotics has unveiled its new humanoid, LUMO. Built on Dobot's proprietary embodied intelligence technology, LUMO learns from real-world experiences and continuously refines its performance. Designed for everyday environments, including homes, educational settings, and public spaces, it showcases how embodied AI is becoming increasingly accessible and practical. Stay up to date with the latest developments in the humanoid industry here: https://lnkd.in/eNdkY_-f #humanoids #humanoid #humanoidrobot #humanoidrobotics

Dyna Robotics has introduced DYNA-2, a World-Action Model trained on over 1 million hours of data. Powered by human egocentric video data, DYNA-2 builds on research that introduced the first human-to-robot scaling law. The findings show that robot performance can improve consistently and predictably as more human data is added, with no signs of reaching a performance plateau. “Action data is scarce, but video is everywhere, and with DYNA-2, we showed that physical intuition doesn’t require millions of hours of training on a robot arm; it can be learned directly from human video. By building a World-Action Model that imagines how the physical world moves before taking action, we give robots spatial reasoning and contact physics that traditional vision-language models simply lack and show that physical AI can scale smoothly and predictably, unlocking commercial-grade automation far faster than previously thought possible,” said Dyna Robotics co-founder Jason Ma. Read more: https://lnkd.in/eXEbeiU3 #humanoids #humanoidrobotics #humanoid #humanoidrobot