Go2-W

Source-backed capabilities

• Workflows: Wheel-leg traversal, stairs, obstacle crossing, app control, secondary development and sensor-enabled mobility.
• Operating environments: Outdoor field environment
• Target markets: Developers, researchers, education users and teams testing lower-cost quadruped mobility.
• Deployment model: Commercial product in Unitree's Go-series ecosystem.
• Navigation and obstacle avoidance

  Research demonstration - 2026-06-19 - The paper builds a deep-reinforcement-learning locomotion controller and autonomous navigation system for the commercially available Go2-W.

  Source
• Autonomous route navigation

  Research demonstration - 2026-06-19 - The paper builds a deep-reinforcement-learning locomotion controller and autonomous navigation system for the commercially available Go2-W.

  Source
• Multi-terrain locomotion

  Claimed - Go2-W combines wheeled travel with legged traversal across mixed outdoor terrain. - environment: stairs and mixed outdoor terrain

  Source
• Stair climbing

  Claimed - Go2-W uses its wheeled-leg configuration to traverse stairs. - environment: stairs and mixed outdoor terrain

  Source

• Racing a Wheeled Quadruped: Active Load Transfer Mitigation via Model Predictive Control

  2026-06-24 - Research Publication - This paper presents a hierarchical control framework using model predictive control (MPC) and reinforcement learning (RL) for active roll control to manage lateral load transfer during autonomous racing of a wheeled quadruped. The framework integrates offline time-optimal raceline generation, an online MPC planner that actively minimizes the lateral Load Transfer Ratio (LTR), and a low-level, whole-body RL policy dep

  Source
• 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.

  Source
• MUJICA: Multi-skill Unified Joint Integration of Control Architecture for Wheeled-Legged Robots

  2026-05-13 - Research Publication - Wheeled-legged robots hold promise for traversing complex terrains and offer superior mobility compared to legged robots.

  Source
• fan-ziqi/robot_lab

  2024-07-06 - Research Publication - The source registers exact model-specific Isaac Lab environments for tracked quadruped, wheeled-quadruped and humanoid platforms.

  Source

Market context

Compact wheeled-legged Go2 variant with in-wheel motors and pneumatic tires.

• Target environment: Education, research, inspection demos, light field robotics and all-terrain mobility experiments.
• Workflow context: Wheel-leg traversal, stairs, obstacle crossing, app control, secondary development and sensor-enabled mobility.
• Customer context: Developers, researchers, education users and teams testing lower-cost quadruped mobility.
• Deployment model: Commercial product in Unitree's Go-series ecosystem.
• Commercial maturity: public product page with detailed parameters and feature list.
• Adoption constraints: Adoption depends on software access, safety controls, payload needs, terrain demands and support availability.
• Market position: Lower-cost wheeled quadruped option beneath Unitree's industrial B-series.
• Adjacent products: Unitree Go2, Unitree B2-W, Unitree B2, Deep Robotics Lite3

Comparable Systems

• LYNX M20

  Deep Robotics - Quadruped

• LYNX M20S

  Deep Robotics - Quadruped

• LYNX S10

  Deep Robotics - Quadruped

• MagicDog-W

  MagicLab - Quadruped

• Unitree As2-W

  Unitree - Quadruped

• Hypertron-SW01

  ASTRALL - Quadruped

Related Systems

• PrimeBOT T1

  PrimeBOT / 上纬启元 - Quadruped