Go2-W Research

Research

  • Inside Unitree's Vertical Integration Strategy - 2026-07-07 - Article - Recent executive remarks and the company's STAR Market prospectus reveal how Unitree is building a vertically integrated robotics manufacturer at scale.
  • This Week in Humanoid Robotics - 2026-04-18 - Note - Funding, deployments, and capability signals across the last 7 days.
  • China’s humanoid push is moving into production - 2026-04-12 - Note - Output, capacity, and supply chains are starting to take shape across the stack
  • Unitree files for Shanghai IPO as humanoid revenue overtakes quadrupeds - 2026-03-20 - Article - Unitree is trying to raise RMB 4.2B on Shanghai’s STAR Market after turning humanoids into its largest revenue line. The filing shows a rare profitable robotics manufacturer, but also a company whose commercial humanoid demand is still…
  • Wheeled-quadruped racing paper controls load transfer on Unitree Go2-W - 2026-06-24 - Research Publication - The paper presents a hierarchical MPC and reinforcement-learning framework for active roll control during autonomous wheeled-quadruped racing. The controller uses a vehicle-dynamics bicycle model of the Unitree Go2-W… - source: arxiv.org
  • Long-Distance Real-World Navigation of the Legged-Wheeled Robot Go2-W Using Deep Reinforcement Learning - 2026-06-19 - Research Publication - The paper builds a deep-reinforcement-learning locomotion controller and autonomous navigation system for the commercially available Go2-W. The controller extends a proprioception-only quadruped policy to the 16-DoF… - source: arxiv.org
  • MUJICA paper validates unified wheeled-legged control on Unitree Go2-W - 2026-05-13 - Research Publication - The MUJICA paper introduces a multi-skill unified control architecture for wheeled-legged robots balancing driving and legged locomotion. The authors validate the framework in simulation and real-world experiments on a… - source: arxiv.org
  • fan-ziqi/robot_lab - 2024-07-06 - Research Publication - robot_lab is an Apache-2.0 reinforcement-learning extension built on NVIDIA Isaac Lab. Its README registers exact model-specific simulation environments across quadruped, wheeled-quadruped and humanoid platforms, including… - source: github.com

View Go2-W overview