Humanoid Robots
85 related stories
AgiBot Proposes 'Worken' Metric to Measure Actual Robot Labor Output
Following the deployment of over 300 robots at Chimelong, AgiBot introduced the "Worken" metric to evaluate actual labor output rather than mere deployment numbers, highlighting the ongoing challenge of scaling on-site engineering support.
Ball Screw Suppliers Await Tesla's Production Ramp-Up Amid Unconverged Humanoid Robot Designs
During Tesla's third-quarter earnings call, Elon Musk defended early production ramp-ups for Optimus despite unfinished hand designs, citing parallel progress in robot manufacturing, supply chain development, hardware design tweaks, and AI software. Meanwhile, Chinese ball screw suppliers are scaling capacity but waiting for actual downstream demand as humanoid robot joint architectures remain unsettled.
RoboMIND Open-Source Dataset Surpasses 50 Million Downloads, Latest 10 Million Reached in 18 Days
The Beijing Humanoid Robot Innovation Center announced on October 26 that the open-source dataset RoboMIND has exceeded 50 million global downloads. The latest 10 million downloads were achieved in just 18 days, accelerating significantly from the 223 days required for the first 10 million and 39 days for the second.
RoboMIND Downloads Surpass 50 Million, With the Latest 10 Million Achieved in Just 18 Days
The Beijing Innovation Center of Humanoid Robotics announced that its open-source dataset, RoboMIND, has exceeded 50 million global downloads. The latest 10 million downloads were achieved in just 18 days, reflecting rapid adoption as the dataset expands to over 400,000 trajectories.
Tesla Begins Optimus Production; Musk Says Reaching 20,000 Units a Week Will Take at Least a Year
Tesla's third-quarter 2026 shareholder letter confirms Optimus has entered early high-volume production at the Fremont factory, marking the first units to meet mass-production quality standards, though the company notes that hardware and manufacturing processes will continue to iterate as it approaches commercial readiness.
UC Berkeley's SuperMimic Slashes Compute for Humanoid Whole-Body Control
Accepted as an oral paper at CoRL 2026, the SuperMimic framework uses a differentiable world model to train humanoid whole-body control on a single GPU in three hours, outperforming previous methods that required massive GPU clusters.
UC Berkeley's SuperMimic Trains Humanoid Whole-Body Control on a Single GPU in 3 Hours, Surpassing 128-GPU Baseline
A UC Berkeley team introduced SuperMimic, a framework that uses a single differentiable world model to scale humanoid whole-body control. The approach trains on a single NVIDIA H100 GPU in 3 hours to outperform the SONIC baseline, which required 128 NVIDIA L40 GPUs over 7 days, reducing GPU-hour costs by more than 1,000 times.
Agile Robots and NVIDIA Launch Agile ONE SN Reference Humanoid for Research Labs
On October 21, NVIDIA expanded its Isaac open robot development platform at GTC Berlin, while Munich-based Agile Robots and NVIDIA simultaneously introduced the Agile ONE SN, a ready-to-use reference humanoid robot targeting academic research.
Tesla Confirms Optimus Production and Early Ramp in Q3 Earnings
In its third-quarter 2026 earnings report released on October 21, Tesla confirmed that the first production-quality Optimus humanoid robots have rolled off the line at its Fremont factory, marking the start of an early ramp for the California project.
HAF-VLA Enables Hierarchical Generation of Coordinated Full-Body Actions in Humanoid Robots
A joint team from Peking University, Tsinghua University, and other institutions has proposed HAF-VLA, a hierarchical framework that enables humanoid robots to generate coordinated full-body actions by sequentially planning movements along the kinematic chain to avoid compensatory instability.
AGIBOT X2 Provides Patient Guidance at Peking University People's Hospital, Logging Over 46,000 Interactions
AgiBot's patient guidance project with Ant A-Fu is operating at Peking University People's Hospital. By September 30, AGIBOT X2 had completed 46,686 interactions over 66 working days.
I-BFM: Unsupervised Reinforcement Learning Enables Robust Humanoid Interaction After Falls
Researchers from Tongji University and Tsinghua University introduce I-BFM, a behavior foundation model that uses forward-backward representation to allow humanoid robots to recover from falls and adapt to disturbances without re-planning trajectories.