
CMoE: Contrastive Mixture of Experts for Motion Control and Terrain Adaptation of Humanoid Robots
CMoE uses contrastive learning to improve MoE expert specialization for humanoid terrain navigation. Validated on Unitree G1, achieving robust gait over 20cm steps and 80cm gaps.
Shihao Ma, Hongjin Chen, Zijun XuMar 3, 2026
Unitree G1MoESim-to-RealMar 3, 2026