Hiking in the Wild: A Scalable Perceptive Parkour Framework for Humanoids
cs.RO, cs.AI
Submitted: 2026-01-12
Updated: 2026-10-13
Comments: Project Page: https://project-instinct.github.io/hiking-in-the-wild
Code: https://github.com/1xtechnologies/wb
Project page: https://projectinstinct.github.io/hiking-in-the-wild
License: http://creativecommons.org/licenses/by/4.0/
The gist: Achieving robust humanoid locomotion in complex, unstructured environments requires transitioning from reactive proprioception to proactive perception.
Terminology
Abstract
Achieving robust humanoid locomotion in complex, unstructured environments requires transitioning from reactive proprioception to proactive perception. However, integrating exteroception remains a significant challenge: existing approaches often fail to achieve high-speed, stable locomotion across diverse, unstructured terrains. In this work, we present Hiking in the Wild, an extensible, end-to-end perceptive legged parkour framework designed for robust humanoid hiking. Our approach maps depth inputs and proprioception directly to joint actions, without relying on external localization and mapping. To ensure safety and training stability, we introduce two key mechanisms: a foothold safety mechanism combining extensible Terrain Edge Detection with Foot Volume Points to reduce catastrophic slippage on edges, and a Flat Patch Sampling strategy that mitigates reward hacking by generating feasible navigation targets. Extensive experiments on the Unitree G1 humanoid robot demonstrate that our policy enables robust traversal of complex terrains at speeds up to 2.5 m/s.
Sources
- Retargeting Matters: General Motion Retargeting for Humanoid Motion Tracking
- Gallant: Voxel Grid-based Humanoid Locomotion and Local-navigation across 3D Constrained Terrains
- Humanoid-Gym: Reinforcement Learning for Humanoid Robot with Zero-Shot Sim2Real Transfer
- MoE-Loco: Mixture of Experts for Multitask Locomotion
- BeyondMimic: From Motion Tracking to Versatile Humanoid Control via Guided Diffusion
- SONIC: Supersizing Motion Tracking for Natural Humanoid Whole-Body Control
- Isaac Lab: A GPU-Accelerated Simulation Framework for Multi-Modal Robot Learning
- Learning Humanoid Locomotion over Challenging Terrain
- Parkour in the Wild: Learning a General and Extensible Agile Locomotion Policy Using Multi-expert Distillation and RL Fine-tuning
- Proximal Policy Optimization Algorithms
- Blind Bipedal Stair Traversal via Sim-to-Real Reinforcement Learning
- Gait-Adaptive Perceptive Humanoid Locomotion with Real-Time Under-Base Terrain Reconstruction
- DPL: Depth-only Perceptive Humanoid Locomotion via Realistic Depth Synthesis and Cross-Attention Terrain Reconstruction
- BeamDojo: Learning Agile Humanoid Locomotion on Sparse Footholds
- Learning Vision-Driven Reactive Soccer Skills for Humanoid Robots
- PvP: Data-Efficient Humanoid Robot Learning with Proprioceptive-Privileged Contrastive Representations
- Robot Parkour Learning
- Humanoid Parkour Learning
Related papers
- FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
- MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
- RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
- ARC: A Reasoning Recipe for Robot Foundation Models
- HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
- APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies