Unitree G-1

The 'Unitree G1' is a robot used to evaluate rapid training of humanoid locomotion policies through reinforcement learning in various challenging conditions.

Papers using Unitree G-1 (6)

Real-Time Gait Adaptation for Quadrupeds using Model Predictive Control and Reinforcement Learning2025 · 2 citesStructural Optimization of Lightweight Bipedal Robot via SERL2024Learning to Walk from Three Minutes of Real-World Data with Semi-structured Dynamics Models2024RobotDancing: Residual-Action Reinforcement Learning Enables Robust Long-Horizon Humanoid Motion Tracking2025Learning Sim-to-Real Humanoid Locomotion in 15 Minutes2025E-SDS: Environment-aware See it, Do it, Sorted - Automated Environment-Aware Reinforcement Learning for Humanoid Locomotion2025