CMoE: Contrastive Mixture of Experts for Motion Control and Terrain Adaptation of Humanoid Robots

Humans primarily rely on walking and running to traverse complex terrains. Similarly, humanoid robots should be able to smoothly transition between walking and running while maintaining natural and stable locomotion. However, unifying gait transition and multi-terrain adaptation within a single policy remains challenging due to gradient interference between tasks and the distribution shift caused by terrain variations. Although Mixture-of-Experts (MoE) architectures can mitigate multi-skill interference, direct joint training often fails to achieve clear expert specialization. To address these challenges, we propose CoRe-MoE, a two-stage reinforcement learning framework that decouples gait generation from terrain adaptation. In the first stage, a stable locomotion policy is learned to produce natural walking and running behaviors with smooth transitions. In the second stage, a terrain-aware MoE branch is introduced, and the gating network is trained with a contrastive objective to learn structured terrain representations and promote expert specialization. The final action is obtained through weighted fusion of the base gait policy and the terrain-aware branch, enabling the policy to preserve stable locomotion while adapting to complex terrains. Extensive simulation results demonstrate that the proposed method outperforms baseline approaches in terms of success rate, locomotion stability, and multi-terrain adaptability. Furthermore, zero-shot deployment on a Unitree G1 humanoid robot validates the effectiveness of our framework, achieving robust walking and running across stairs, slopes, steps, obstacles, and unstructured outdoor terrains while maintaining accurate foothold control and dynamic stability.

Perceptive legged locomotion over discontinuous terrain (e.g., stairs, gaps, and obstacles) requires adaptive behavior, as a single conservative gait cannot produce the anticipatory maneuvers needed for abrupt topology changes. Cast as multi-task reinforcement learning, this problem introduces a tension between sharing and separation. Tasks use a common locomotion base but have conflicting rewards, so a policy must share behavior while avoiding value interference. Prior work addresses only one side, with monolithic policies sacrificing specialization and hierarchical sub-policies sacrificing generalization across transitions and unseen terrain. We propose CTS-MoE, which combines a dense mixture-of-experts actor with perception-based gating to compose shared behaviors and a multi-critic with task-specific value heads to prevent interference. The model is trained end-to-end in a single-stage concurrent teacher-student setup that handles partial observability and avoids sequential distillation, with task labels used only during training. At deployment, routing depends solely on perception, allowing terrain adaptation without a high-level selector or terrain classifier. Experiments on a Unitree Go1 in simulation and on hardware across seen and unseen terrains show task-aware specialization, with lower tracking error and higher success rates than monolithic baselines. Project Website: https://cts-moe.github.io/ .

Falling is an inherent risk for humanoid robots operating in unstructured environments. Existing reinforcement learning methods that leverage expert motion priors are predominantly trained on flat-ground fall-recovery tasks and typically rely on hard switching between separate recovery and locomotion controllers. As a result, such policies struggle to achieve smooth and robust recovery behaviors when deployed on complex terrains such as slopes and gravel. This paper presents \textbf{CG-MuTra}, a unified continuously-gated multi-scale discriminator framework for multi-terrain adaptive fall recovery. CG-MuTra introduces a proprioceptively-derived continuous gate $α= f(z_{\mathrm{root}}, s)$ that softly blends three discriminators operating at different temporal horizons: frame-level stability ($Φ_{\mathrm{frame}}$, $H=1$), temporal smoothness ($Φ_{\mathrm{seq}}$, $H=5$), and gait periodicity ($Φ_{\mathrm{gait}}$, $H=10$). This design enables seamless recovery-to-locomotion transitions without explicit mode switching. Furthermore, we propose a Terrain-Pose Risk Coupling Sampler (TPRCS) that explicitly couples dangerous edge initial poses with terrain dynamics during training, forming a closed-loop synergy with the terrain-privileged shaping term $Ξ_κ$. We validate CG-MuTra on a Unitree G1 humanoid across grass, slopes ($10^\circ$--$15^\circ$), and gravel in both simulation and hardware. Experimental results demonstrate that CG-MuTra achieves smooth, highly robust fall recovery and locomotion transitions across multiple terrains while maintaining a single deployable policy.