Robotic Magazine

Twitter account for Robotic Magazine. Retweets are for informational purposes only, no endorsements implied.

[Robotic Magazine @RoboticMagazine]

How do humanoid robots walk?
Walking requires balance control, state estimation, foot placement, inverse dynamics, sensors, actuators, simulation, and increasingly AI

https://t.co/ofLUqk5FNy

#HumanoidRobots #Robotics #AI #RobotLearning #PhysicalAI #RoboticsEngineering

[Jacob H. Rothschild @ja_rothschild]

How a robot arm is controlled, explained for ML people new to robot learning. First of the explainers from my own speedrun.

Next one will be on ACT. Follow me to catch it. https://t.co/g25ayJDVhe

[Robotic Magazine @RoboticMagazine]

LLMs as we know it: They work by tokens.

Two separate papers propose different ways. Can they be realistically applied and the LLM architecture get far more efficient soon?

https://t.co/PzMg0H5BZD

#LLM
#artificialintelligence
#largelanguagemodels

[Robotic Magazine @RoboticMagazine]

Open code

[Runyi (Ingrid) Yu✈️CoRL @Runyi_Ingrid_Yu]

🎉 Excited to share our new work: UMR! 🎉

Unified Motion Retargeting (UMR) learns dense point-cloud correspondences to transfer human motion across diverse humanoid embodiments. It supports locomotion and contact-rich data.

Code is now open!
🌐: https://t.co/5EE6m8fNP9

[Space and Technology @spaceandtech_]

Meet Tron 2, a robot from China-based LimX Dynamics that can change its body for different jobs.

It can use a fixed base for precise tasks, a wheeled-leg base to carry heavy loads, or two legs to walk and climb stairs.

The arms and brain stay the same, while the lower body changes depending on the mission.

[Robotic Magazine @RoboticMagazine]

@techniahqrobot For Optimus as far as I know Musk's priority was hands.

[TianGong Robotics @Xhumanoid_BJ]

TianGong Ultra has won the gold medal in the 100m Large-Size category at the 2nd World Humanoid Robot Games with a time of 8.64 seconds, successfully defending its championship and once again surpassing the human world record！

[Robotic Magazine @RoboticMagazine]

The most interesting part isn't just the simulator—it’s turning VR headsets into scalable data-generation tools for dexterous robots. Combining contact-rich simulation with VR teleoperation could help solve the data bottleneck in robot learning.

[Lukas Ziegler @lukas_m_ziegler]

Meta just open-sourced its dexterity stack! 🪬

Most physics simulators were built for things that move through space.

Walking robots, drones, cars. Contact is the part they approximate worst, and obviously dexterous manipulation is nothing but contact.

Project SuperDex, from Meta Reality Labs Research, is built the other way around, a contact-first physics engine with the whole platform stacked on top of it.

The cool part is that it's on GitHub.

The engine runs one solver across rigid bodies, soft bodies, rods and tendons, shells and cloth, in the same model.

→ Non-convex collision with accurate contact force distributions, so a multi-finger grasp gets simulated rather than approximated
→ Tactile sensors and soft contact as first-class primitives
→ Numerical stability without the tight time-step limits explicit solvers force on you
→ Constraint-aware inverse kinematics running on the same optimization core as the forward dynamics

Then the data layer. Put on a Quest 3, teleoperate the simulated hand with haptic feedback, and generate demonstration datasets without touching real hardware.

They show a shape-sorting policy trained entirely in simulation and deployed zero-shot on a real robotic hand.

Robot hands are getting good. Data for them isn't that fast.

Meta is betting the cheapest way to collect contact-rich demonstrations is a headset people already own, pointed at a simulator instead of a game.

🔗 Here's the project page: https://t.co/bFCmZrp4jA

~~

♻️ Join the weekly robotics newsletter, and never miss any news → https://t.co/GoA3ZuwoPB

[Léo @LeoKharon]

NEW ROBOT: First transformer humanoid !

HFUN-TECH released a robot that can autonomously reconfigure between a wheel-foot humanoid and a four-legged quadruped, switching modes on its own based on terrain via a unified control framework.

You can even carry it as a suitcase, and ride it to move around!

It carries a flip camera, a 45-degree tilted interaction screen and a multi-microphone array, and is pitched for home companionship, content creation and outdoor use.
It debuted at the 2026 World Artificial Intelligence Conference (WAIC, July 17-20, Shanghai).

I also found an alomst identical robot marketed as the "PrimeBOT Qiyuan T1" from a Shanghai startup PrimeBOT, so I cannot really make sense of it 🤔

[Robotic Magazine @RoboticMagazine]

@jacksonhinkle Why ? Because they will do Kung Fu ?

[Space and Technology @spaceandtech_]

Wuji Tech has unveiled the Wuji Hand 2, a robotic hand with fast and human-like finger movements.

Built with metal components, gears, and compact electric motors, it offers high precision and control.

Advanced sensors automatically adjust grip strength, allowing it to handle different objects securely and smoothly.

[Robotic Magazine @RoboticMagazine]

What is Physical AI?

How do we transition from LLM Chatbots to Physical AI?

https://t.co/PhOoqkYDoD

#chatbots
#physicalAI

[Robotic Magazine @RoboticMagazine]

@Rainmaker1973 what's the solution? AI analyzing AI content and eliminating those publishers from posting again?

[Space and Technology @spaceandtech_]

Shanghai-based robotics company AGIBOT has updated its Lingxi X2 humanoid robot with smarter motion capabilities.

The robot can detect moving objects around it, predict their path, and quickly move out of the way.

Lingxi X2 can also climb stairs, keep its balance on uneven surfaces, and move more smoothly.

[SciTech Era @SciTechera]

Wow. This is crazy.

Researchers built an open-source humanoid robot that learned to walk, run, balance and even perform K-pop dance moves in just 7 days 🤯

ROBOTIS AI Sapiens uses NVIDIA Isaac Sim for training, motion retargeting to transfer human movements to the robot, and reinforcement learning to refine its skills before deployment in the real world.

Powered by NVIDIA Jetson Orin NX and the new DYNAMIXEL-Q actuators, the humanoid can learn complex full body behaviors in simulation and then execute them physically.

[Massimo @Rainmaker1973]

American research institute IHMC’s six legged robot is built for speed and off road mobility.

[Robotic Magazine @RoboticMagazine]

@Eng_china5 Lol

[Robotic Magazine @RoboticMagazine]

@shub0414 Why?

[Robotic Magazine @RoboticMagazine]

@Rainmaker1973 Loool😂

[Robotic Magazine @RoboticMagazine]

@TheSpacerr Eating