# Learning Whole-Body Humanoid Locomotion via Motion Generation and Motion Tracking

arXiv: https://arxiv.org/abs/2604.17335 · HTML: https://mlsanity.com/paper/2604.17335/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Apr 2026.

## Built on by (most cited first, 9 of 9)

- [SceneBot: Contact-Prompted General Humanoid Whole Body Tracking with Scene-Interaction](https://mlsanity.com/paper/2606.27581/) (2026)
- [TEXEDO : Test Time Scaling for Controller-aware Language-conditioned Humanoid Motion Generation](https://mlsanity.com/paper/2606.22998/) (2026)
- [VLK: Learning Humanoid Loco-Manipulation from Synthetic Interactions in Reconstructed Scenes](https://mlsanity.com/paper/2606.30645/) (2026)
- [LadderMan: Learning Humanoid Perceptive Ladder Climbing](https://mlsanity.com/paper/2606.05873/) (2026)
- [MIME: Multimodal Interactive Motion Encoder](https://mlsanity.com/paper/2607.22702/) (2026)
- [GigaBrain-WBC-0.5: A Behavior World Model for Robust Humanoid Whole-Body Tracking with Environment Interaction](https://mlsanity.com/paper/2608.18234/) (2026)
- [Towards Professional Tennis Styles for Humanoid Robots with Adaptive Motion Planning and Tracking](https://mlsanity.com/paper/2608.20087/) (2026)
- [CAP: Continuously Adaptive Perception-Blind Humanoid Locomotion via Learned Denoising](https://mlsanity.com/paper/2609.11553/) (2026)
- [Learning Expressive and Compositional Motion Representation via Spectral Skills](https://mlsanity.com/paper/2609.37677/) (2026)

## Abstract (arXiv)

Whole-body humanoid locomotion is challenging due to high-dimensional control, morphological instability, and the need for real-time adaptation to various terrains using onboard perception. Directly applying reinforcement learning (RL) with reward shaping to humanoid locomotion often leads to lower-body-dominated behaviors, whereas imitation-based RL can learn more coordinated whole-body skills but is typically limited to replaying reference motions without a mechanism to adapt them online from perception for terrain-aware locomotion. To address this gap, we propose a whole-body humanoid locomotion framework that combines skills learned from reference motions with terrain-aware adaptation. We first train a diffusion model on retargeted human motions for real-time prediction of terrain-aware reference motions. Concurrently, we train a whole-body reference tracker with RL using this motion data. To improve robustness under imperfectly generated references, we further fine-tune the tracker with a frozen motion generator in a closed-loop setting. The resulting system supports directional goal-reaching control with terrain-aware whole-body adaptation, and can be deployed on a Unitree G1 humanoid robot with onboard perception and computation. The hardware experiments demonstrate successful traversal over boxes, hurdles, stairs, and mixed terrain combinations. Quantitative results further show the benefits of incorporating online motion generation and fine-tuning the motion tracker for improved generalization and robustness.