# Humanoid Whole-Body Locomotion on Narrow Terrain via Dynamic Balance and Reinforcement Learning

arXiv: https://arxiv.org/abs/2502.17219 · HTML: https://mlsanity.com/paper/2502.17219/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Placed in RL for robot locomotion and manipulation, one of 15 directions in Deep reinforcement learning methods.
- Builds on 26 of its 43 references that are in the map.
- First posted on arXiv 24 Feb 2025.

## Placed in

- Deep reinforcement learning methods / [RL for robot locomotion and manipulation](https://mlsanity.com/deeprl/rl-for-robot-locomotion-and-manipulation/)

## Builds on (most cited first, 26 of 26)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning](https://mlsanity.com/paper/2108.10470/) (2021)
- [Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learning](https://mlsanity.com/paper/2109.11978/) (2021)
- [Asymmetric Actor Critic for Image-Based Robot Learning](https://mlsanity.com/paper/1710.06542/) (2017)
- [Extreme Parkour with Legged Robots](https://mlsanity.com/paper/2309.14341/) (2023)
- [Robot Parkour Learning](https://mlsanity.com/paper/2309.05665/) (2023)
- [Walk These Ways: Tuning Robot Control for Generalization with Multiplicity of Behavior](https://mlsanity.com/paper/2212.03238/) (2022)
- [Advancing Humanoid Locomotion: Mastering Challenging Terrains with Denoising World Model Learning](https://mlsanity.com/paper/2408.14472/) (2024)
- [Humanoid-Gym: Reinforcement Learning for Humanoid Robot with Zero-Shot Sim2Real Transfer](https://mlsanity.com/paper/2404.05695/) (2024)
- [DiffuseLoco: Real-Time Legged Locomotion Control with Diffusion from Offline Datasets](https://mlsanity.com/paper/2404.19264/) (2024)
- [BeamDojo: Learning Agile Humanoid Locomotion on Sparse Footholds](https://mlsanity.com/paper/2502.10363/) (2025)
- [A Unified MPC Framework for Whole-Body Dynamic Locomotion and Manipulation](https://mlsanity.com/paper/2103.00946/) (2021)
- [Perceptive Locomotion through Nonlinear Model Predictive Control](https://mlsanity.com/paper/2208.08373/) (2022)
- [Lifelike Agility and Play in Quadrupedal Robots using Reinforcement Learning and Generative Pre-trained Models](https://mlsanity.com/paper/2308.15143/) (2023)
- [Leveraging Symmetry in RL-based Legged Locomotion Control](https://mlsanity.com/paper/2403.17320/) (2024)
- [Robust Quadrupedal Locomotion via Risk-Averse Policy Learning](https://mlsanity.com/paper/2308.09405/) (2023)
- [Learning to Walk from Three Minutes of Real-World Data with Semi-structured Dynamics Models](https://mlsanity.com/paper/2410.09163/) (2024)
- [Bridging the Sim-to-Real Gap from the Information Bottleneck Perspective](https://mlsanity.com/paper/2305.18464/) (2023)
- [BiConMP: A Nonlinear Model Predictive Control Framework for Whole Body Motion Planning](https://mlsanity.com/paper/2201.07601/) (2022)
- [Embrace Collisions: Humanoid Shadowing for Deployable Contact-Agnostics Motions](https://mlsanity.com/paper/2502.01465/) (2025)
- [Achieving Stable High-Speed Locomotion for Humanoid Robots with Deep Reinforcement Learning](https://mlsanity.com/paper/2409.16611/) (2024)
- [Multi-contact MPC for Dynamic Loco-manipulation on Humanoid Robots](https://mlsanity.com/paper/2209.08662/) (2022)
- [Decentralized Motor Skill Learning for Complex Robotic Systems](https://mlsanity.com/paper/2306.17411/) (2023)
- [Learning Bipedal Walking on a Quadruped Robot via Adversarial Motion Priors](https://mlsanity.com/paper/2407.02282/) (2024)
- [HiLo: Learning Whole-Body Human-like Locomotion with Motion Tracking Controller](https://mlsanity.com/paper/2502.03122/) (2025)
- [ZMP support areas for multi-contact mobility under frictional constraints](https://mlsanity.com/paper/1510.03232/) (2015)

## Built on by (most cited first, 11 of 11)

- [KungfuBot: Physics-Based Humanoid Whole-Body Control for Learning Highly-Dynamic Skills](https://mlsanity.com/paper/2506.12851/) (2025)
- [TextOp: Real-time Interactive Text-Driven Humanoid Robot Motion Generation and Control](https://mlsanity.com/paper/2602.07439/) (2026)
- [KungfuBot2: Learning Versatile Motion Skills for Humanoid Whole-Body Control](https://mlsanity.com/paper/2509.16638/) (2025)
- [DreamPolicy: A Unified World-model Policy for Scalable Humanoid Locomotion](https://mlsanity.com/paper/2505.18780/) (2025)
- [Gait-Adaptive Perceptive Humanoid Locomotion with Real-Time Under-Base Terrain Reconstruction](https://mlsanity.com/paper/2512.07464/) (2025)
- [RobotDancing: Residual-Action Reinforcement Learning Enables Robust Long-Horizon Humanoid Motion Tracking](https://mlsanity.com/paper/2509.20717/) (2025)
- [SafeFlow: Real-Time Text-Driven Humanoid Whole-Body Control via Physics-Guided Rectified Flow and Selective Safety Gating](https://mlsanity.com/paper/2603.23983/) (2026)
- [Learning Impact-Rich Rotational Maneuvers via Centroidal Velocity Rewards and Sim-to-Real Techniques: A One-Leg Hopper Flip Case Study](https://mlsanity.com/paper/2505.12222/) (2025)
- [Robust RL Control for Bipedal Locomotion with Closed Kinematic Chains](https://mlsanity.com/paper/2507.10164/) (2025)
- [CMR: Contractive Mapping Embeddings for Robust Humanoid Locomotion on Unstructured Terrains](https://mlsanity.com/paper/2602.03511/) (2026)
- [Reinforcement Learning-Based Control for an Inline Skating Humanoid Robot](https://mlsanity.com/paper/2606.31807/) (2026)

## Abstract (arXiv)

Humans possess delicate dynamic balance mechanisms that enable them to maintain stability across diverse terrains and under extreme conditions. However, despite significant advances recently, existing locomotion algorithms for humanoid robots are still struggle to traverse extreme environments, especially in cases that lack external perception (e.g., vision or LiDAR). This is because current methods often rely on gait-based or perception-condition rewards, lacking effective mechanisms to handle unobservable obstacles and sudden balance loss. To address this challenge, we propose a novel whole-body locomotion algorithm based on dynamic balance and Reinforcement Learning (RL) that enables humanoid robots to traverse extreme terrains, particularly narrow pathways and unexpected obstacles, using only proprioception. Specifically, we introduce a dynamic balance mechanism by leveraging an extended measure of Zero-Moment Point (ZMP)-driven rewards and task-driven rewards in a whole-body actor-critic framework, aiming to achieve coordinated actions of the upper and lower limbs for robust locomotion. Experiments conducted on a full-sized Unitree H1-2 robot verify the ability of our method to maintain balance on extremely narrow terrains and under external disturbances, demonstrating its effectiveness in enhancing the robot's adaptability to complex environments. The videos are given at https://whole-body-loco.github.io.