Unitree Go-2

The 'Unitree Go-2' is a quadruped robot used to evaluate safe locomotion in unstructured environments, focusing on long-horizon goal progress, passability over uneven terrain, and collision avoidance against high-speed dynamic obstacles.

Papers using Unitree Go-2 (10)

Bayesian Optimization for Learning Nonlinear MPC in Autonomous Agent Navigation2026FlashNav: Ultra-Fast Policy Training for Robot Navigation within 20 Seconds2026SLowRL: Safe Low-Rank Adaptation Reinforcement Learning for Locomotion2026Articulated-Body Dynamics Network: Dynamics-Grounded Prior for Robot Learning2026UEREBot: Learning Safe Quadrupedal Locomotion under Unstructured Environments and High-Speed Dynamic Obstacles2026MS-PPO: Morphological-Symmetry-Equivariant Policy for Legged Robot Locomotion2025PGTT: Phase-Guided Terrain Traversal for Perceptive Legged Locomotion2025Towards Embodiment Scaling Laws in Robot Locomotion2025McARL:Morphology-Control-Aware Reinforcement Learning for Generalizable Quadrupedal Locomotion2025RANDPOL: Parameter-Efficient End-to-End Quadruped Locomotion via Randomized Policy Learning2025