# Learning Humanoid Locomotion with World Model Reconstruction

arXiv: https://arxiv.org/abs/2502.16230 · HTML: https://mlsanity.com/paper/2502.16230/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Placed in Humanoid and legged locomotion world models, one of 11 directions in World models.
- Builds on 28 of its 35 references that are in the map.
- First posted on arXiv 22 Feb 2025.

## Placed in

- World models / [Humanoid and legged locomotion world models](https://mlsanity.com/wm/humanoid-and-legged-locomotion-world-models/)

## Builds on (most cited first, 28 of 28)

- [AMASS: Archive of Motion Capture as Surface Shapes](https://mlsanity.com/paper/1904.03278/) (2019)
- [Fast Transformer Decoding: One Write-Head is All You Need](https://mlsanity.com/paper/1911.02150/) (2019)
- [Learning Quadrupedal Locomotion over Challenging Terrain](https://mlsanity.com/paper/2010.11251/) (2020)
- [RMA: Rapid Motor Adaptation for Legged Robots](https://mlsanity.com/paper/2107.04034/) (2021)
- [Learning robust perceptive locomotion for quadrupedal robots in the wild](https://mlsanity.com/paper/2201.08117/) (2022)
- [Orbit: A Unified Simulation Framework for Interactive Robot Learning Environments](https://mlsanity.com/paper/2301.04195/) (2023)
- [Real-World Humanoid Locomotion with Reinforcement Learning](https://mlsanity.com/paper/2303.03381/) (2023)
- [ANYmal Parkour: Learning Agile Navigation for Quadrupedal Robots](https://mlsanity.com/paper/2306.14874/) (2023)
- [Robot Parkour Learning](https://mlsanity.com/paper/2309.05665/) (2023)
- [Expressive Whole-Body Control for Humanoid Robots](https://mlsanity.com/paper/2402.16796/) (2024)
- [Reinforcement Learning for Versatile, Dynamic, and Robust Bipedal Locomotion Control](https://mlsanity.com/paper/2401.16889/) (2024)
- [Humanoid Parkour Learning](https://mlsanity.com/paper/2406.10759/) (2024)
- [Blind Bipedal Stair Traversal via Sim-to-Real Reinforcement Learning](https://mlsanity.com/paper/2105.08328/) (2021)
- [Concurrent Training of a Control Policy and a State Estimator for Dynamic and Robust Legged Locomotion](https://mlsanity.com/paper/2202.05481/) (2022)
- [Humanoid Locomotion as Next Token Prediction](https://mlsanity.com/paper/2402.19469/) (2024)
- [DreamWaQ: Learning Robust Quadrupedal Locomotion With Implicit Terrain Imagination via Deep Reinforcement Learning](https://mlsanity.com/paper/2301.10602/) (2023)
- [DTC: Deep Tracking Control](https://mlsanity.com/paper/2309.15462/) (2023)
- [Advancing Humanoid Locomotion: Mastering Challenging Terrains with Denoising World Model Learning](https://mlsanity.com/paper/2408.14472/) (2024)
- [Adapting Rapid Motor Adaptation for Bipedal Robots](https://mlsanity.com/paper/2205.15299/) (2022)
- [Humanoid-Gym: Reinforcement Learning for Humanoid Robot with Zero-Shot Sim2Real Transfer](https://mlsanity.com/paper/2404.05695/) (2024)
- [Learning Humanoid Locomotion with Perceptive Internal Model](https://mlsanity.com/paper/2411.14386/) (2024)
- [Sparsity Winning Twice: Better Robust Generalization from More Efficient Training](https://mlsanity.com/paper/2202.09844/) (2022)
- [HumanMimic: Learning Natural Locomotion and Transitions for Humanoid Robot via Wasserstein Adversarial Imitation](https://mlsanity.com/paper/2309.14225/) (2023)
- [Learning Humanoid Locomotion over Challenging Terrain](https://mlsanity.com/paper/2410.03654/) (2024)
- [Revisiting Reward Design and Evaluation for Robust Humanoid Standing and Walking](https://mlsanity.com/paper/2404.19173/) (2024)
- [Identifying Terrain Physical Parameters from Vision -- Towards Physical-Parameter-Aware Locomotion and Navigation](https://mlsanity.com/paper/2408.16567/) (2024)
- [Linear Policies are Sufficient to Realize Robust Bipedal Walking on Challenging Terrains](https://mlsanity.com/paper/2109.12665/) (2021)
- [MPC for Humanoid Gait Generation: Stability and Feasibility](https://mlsanity.com/paper/1901.08505/) (2019)

## Built on by (most cited first, 13 of 13)

- [A Comprehensive Survey on World Models for Embodied AI](https://mlsanity.com/paper/2510.16732/) (2025)
- [A Survey: Learning Embodied Intelligence from Physical Simulators and World Models](https://mlsanity.com/paper/2507.00917/) (2025)
- [MoRE: Mixture of Residual Experts for Humanoid Lifelike Gaits Learning on Complex Terrains](https://mlsanity.com/paper/2506.08840/) (2025)
- [DreamPolicy: A Unified World-model Policy for Scalable Humanoid Locomotion](https://mlsanity.com/paper/2505.18780/) (2025)
- [HAIC: Humanoid Agile Object Interaction Control via Dynamics-Aware World Model](https://mlsanity.com/paper/2602.11758/) (2026)
- [Contrastive Representation Learning for Robust Sim-to-Real Transfer of Adaptive Humanoid Locomotion](https://mlsanity.com/paper/2509.12858/) (2025)
- [SplitAdapter: Load-Aware Humanoid Loco-Manipulation via Factorized Adaptation](https://mlsanity.com/paper/2606.03297/) (2026)
- [PvP: Data-Efficient Humanoid Robot Learning with Proprioceptive-Privileged Contrastive Representations](https://mlsanity.com/paper/2512.13093/) (2025)
- [Towards Bridging the Gap between Large-Scale Pretraining and Efficient Finetuning for Humanoid Control](https://mlsanity.com/paper/2601.21363/) (2026)
- [World-Model-Augmented Visual Locomotion for Humanoids on Foothold-Constrained Terrain](https://mlsanity.com/paper/2609.02542/) (2026)
- [DAWN: Noise-Robust Quadruped Parkour via Depth-Denoising World Models](https://mlsanity.com/paper/2609.29092/) (2026)
- [Rethinking World Models for Safety-Critical Embodied Systems](https://mlsanity.com/paper/2609.03774/) (2026)
- [LocoWM: High-Precision Locomotion through World-Model-Guided Residual Adaptation](https://mlsanity.com/paper/2609.39179/) (2026)

## Abstract (arXiv)

Humanoid robots are designed to navigate environments accessible to humans using their legs. However, classical research has primarily focused on controlled laboratory settings, resulting in a gap in developing controllers for navigating complex real-world terrains. This challenge mainly arises from the limitations and noise in sensor data, which hinder the robot's understanding of itself and the environment. In this study, we introduce World Model Reconstruction (WMR), an end-to-end learning-based approach for blind humanoid locomotion across challenging terrains. We propose training an estimator to explicitly reconstruct the world state and utilize it to enhance the locomotion policy. The locomotion policy takes inputs entirely from the reconstructed information. The policy and the estimator are trained jointly; however, the gradient between them is intentionally cut off. This ensures that the estimator focuses solely on world reconstruction, independent of the locomotion policy's updates. We evaluated our model on rough, deformable, and slippery surfaces in real-world scenarios, demonstrating robust adaptability and resistance to interference. The robot successfully completed a 3.2 km hike without any human assistance, mastering terrains covered with ice and snow.