Hiking in the Wild: A Scalable Perceptive Parkour Framework for Humanoids

Shaoting Zhu; Ziwen Zhuang; Mengjie Zhao; Kun-Ying Lee; Hang Zhao

cs.ROJan 12, 2026

Hiking in the Wild: A Scalable Perceptive Parkour Framework for Humanoids

Authors: Shaoting Zhu, Ziwen Zhuang, Mengjie Zhao, Kun-Ying Lee, Hang Zhao

Organizations: IIIS, Tsinghua University · Shanghai Qi Zhi Institute · Department of Computer Science and Technology, Tsinghua University

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.

Figures & tables

Figure 1: Hiking in the Wild. Our framework enables a humanoid robot to traverse diverse terrains in the wild. The robot can run at a maximum speed of 2.5 m/s over complex terrain. It can also negotiate stairs, gaps, high platforms, and ramps. Relying on depth images for perception, our extensible end-to-end framework achieves robust performance across these scenarios.

Figure 2: System overview. Our framework trains an end-to-end policy using simulated depth and proprioception. To ensure safety and agility on complex terrains, we incorporate Extensible Edge Penalization to avoid risky footholds and Position-Based Command Generation for precise tracking. The trained policy is directly deployed to the real robot (Zero-shot) using only a 60 Hz onboard depth camera as exteroception, achieving highly dynamic locomotion without explicit localization or map reconstruction.

Figure 3: Depth processing: Top row shows $\mathcal{F}_{sim}$ on synthetic data, and bottom row shows $\mathcal{F}_{real}$ on real-world data.

Figure 4: Terrain edge contact penalization. Left: automatically detected edges across diverse terrains. Right: volume points distributed within the foot manifold for penetration penalization.

Figure 5: Snapshots of the humanoid robot traversing diverse indoor and outdoor environments via zero-shot transfer: (a) running ascent onto a high platform; (b) running descent from a high platform; (c) running on a grassy slope; (d) stair ascent; (e) stair descent; (f) traversing a discrete gap.

Figure 7: Left: the robot slips and falls after stepping on a stair edge. Right: edge detector visualizations on new and noisy terrains.

Figure 8: Visualization of foothold placement.

	Success Rate (%) $\uparrow$									Mean Reaching Time (s) $\downarrow$
Method	Large Box	Ramp	Small Box	Rough	Stair Down	Platform down	Stair Up	Platform up	Gap	Large Box	Ramp	Small Box	Rough	Stair Down	Platform down	Stair Up	Platform up	Gap
w/o depth history	100.0	100.0	1.66	100.0	99.88	100.0	100.0	100.0	100.0	6.20	6.72	11.68	5.78	5.33	5.81	6.54	5.89	5.79
w/o position-based	23.13	100.0	90.68	100.0	99.59	100.0	95.18	11.70	100.0	9.41	5.74	11.32	5.72	6.77	7.07	6.79	10.57	5.70
w/o AMP	13.75	99.94	0.00	100.0	98.39	99.47	0.00	0.00	99.94	9.81	5.68	–	6.50	6.89	7.40	–	–	6.07
10Hz height map	99.40	100.0	15.28	100.0	99.60	100.0	100.0	95.21	100.0	6.51	6.01	14.73	6.34	4.40	5.63	5.63	6.03	6.40
w/o depth	38.94	100.0	3.33	100.0	99.12	99.93	94.54	0.00	67.95	7.88	8.48	10.59	7.75	5.39	6.72	7.12	–	7.58

Table 2: Quantitative results in simulation

Appendix figures & tables7 assets

Supplementary material from the paper’s appendix.

Appendix

Space	Signal	Dim	Description
Actor Obs	Base Angular Velocity $\boldsymbol{\omega}_{t}$	$3$	IMU gyroscope
	Projected Gravity $\mathbf{g}_{t}$	$3$	Gravity direction in base frame
	Velocity Commands $\mathbf{c}_{t}$	$3$	$(v_{x},v_{y},\omega_{z})$
	Joint Positions $\mathbf{q}_{t}$	$29$	29-DoF joint angles
	Joint Velocities $\dot{\mathbf{q}}_{t}$	$29$	29-DoF joint velocities
	Last Action $\mathbf{a}_{t-1}$	$29$	Previous target joint positions

Appendix

Table 3: Observation and action space specification.

Observation Term	Scale	Noise Type	Noise Parameters
Base Angular Velocity ( $\omega_{t}$ )	$0.25$	Uniform	$\mathcal{U}(-0.2,0.2)$ rad/s
Projected Gravity ( $\mathbf{g}_{t}$ )	$1.0$	Uniform	$\mathcal{U}(-0.05,0.05)$
Velocity Commands ( $\mathbf{c}_{t}$ )	$1.0$	None	N/A
Joint Positions ( $q_{t}$ )	$1.0$	Uniform	$\mathcal{U}(-0.01,0.01)$ rad
Joint Velocities ( $\dot{q}_{t}$ )	$0.05$	Uniform	$\mathcal{U}(-0.5,0.5)$ rad/s
Last Action ( $a_{t-1}$ )	$1.0$	None	N/A

Appendix

Table 4: Detailed policy proprioceptive observation space, scaling factors, and noise models.

Reward Term	Weight	Mathematical Formulation
Task Reward
Linear Vel Tracking ( $v_{xy}$ )	$2.0$	$\exp(-\\|\mathbf{v}_{xy}^{*}-\mathbf{v}_{xy}\\|^{2}/0.5^{2})$
Angular Vel Tracking ( $\omega_{z}$ )	$2.0$	$\exp(-(\omega_{z}^{*}-\omega_{z})^{2}/0.5^{2})$
Heading Error	$-1.0$	$\|\omega_{z}^{*}\|$
Don’t Wait	$-0.5$	$\mathbb{I}(v_{x}^{*}>0.3)\cdot(\mathbb{I}(v_{x}<0.15)+\mathbb{I}(v_{x}<0)+\mathbb{I}(v_{x}<-0.15))$
Is Alive	$3.0$	$+1$

Appendix

Table 5: Detailed specifications of reward terms, weights, and mathematical formulations.

Figure 9: Flat patches on different terrains.

Parameter	Value
CNN channels	$[4]$
CNN kernel sizes	$[3]$
CNN strides	$[1]$
CNN paddings	$[1]$
CNN pooling	MaxPool
Encoder projection units	$[256,256]$

Appendix

Table 6: Detailed hyperparameters for the network architecture.

Terrain Settings		Command Range (walking)			Command Range (run)
Terrain Type	Geometric Parameters	Prop.	$\mathbf{v_{x}}$ (m/s)	$\mathbf{\omega_{z}}$ (rad/s)	Prop.	$\mathbf{v_{x}}$ (m/s)	$\mathbf{\omega_{z}}$ (rad/s)
Rough	Perlin Noise Scale $\in[0.0,0.1]$ m	$5\%$	$[0.45,1.0]$	$[-1.0,1.0]$	$20\%$	$[1.95,3.05]$	$[-1.0,1.0]$
Rough (Stand)	Perlin Noise Scale $\in[0.0,0.1]$ m	$5\%$	$0.0$	$[-1.0,1.0]$	$5\%$	$0.0$	$[-1.0,1.0]$
Square Gaps	Gap Dist $\in[0.1,0.7]$ m, Depth $\in[0.4,0.6]$ m	$10\%$	$[0.45,0.8]$	$[-1.0,1.0]$	$-$	$-$	$-$
Stairs Down	Step Height $\in[0.05,0.23]$ m, Width $0.3$ m	$15\%$	$[0.45,0.8]$	$[-1.0,1.0]$	$-$	$-$	$-$
Platform Down	Platform Height $\in[0.05,0.45]$ m	$10\%$	$[0.45,0.8]$	$[-1.0,1.0]$	$25\%$	$[1.95,3.05]$	$[-1.0,1.0]$

Appendix

Table 7: Detailed specifications of terrain types and their corresponding velocity command ranges for walking and running modes. Note that the lateral velocity command

v_{y}

is set to

0

for all terrain types.

Terrain Type	Evaluation Geometry
Stair up/down	Step height $0.20$ m
Large box	Height $0.40$ m
Platform up/down	Platform height $0.40$ m
Ramp	Slope $0.40$ rad
Gap	Gap distance $0.60$ m
Rough terrain	Noise scale $0.05$

Appendix

Table 8: Terrain geometry settings used for the simulation comparison and ablation study.

Humanoid Robot Locomotion

Humanoid robot locomotion studies how bipedal robots walk, run, recover from disturbances, and traverse varied terrain.

See all 145 papers

Echo in the Steps: Learning Perceptive Humanoid Parkour with Gated Memory
Sep 24, 2026Ming-Ju Lee, Zizhuo Wang, Shaoting Zhu +3Legged Robotics Humanoid Robot Locomotion
Tsinghua University
Perceptive Humanoid Parkour: Chaining Dynamic Human Skills via Motion Matching
Feb 17, 2026Zhen Wu, Xiaoyu Huang, Lujie Yang +8Humanoid Robot Locomotion Robot Skill Learning
Amazon FAR · UC Berkeley · CMU +1
PUMA: Perception-driven Unified Foothold Prior for Mobility Augmented Quadruped Parkour
Jan 22, 2026Liang Wang, Kanzhong Yao, Yang Liu +4Legged Robotics Terrain-Aware Robot Locomotion
Institute of Cyber-Systems and Control, Zhejiang University, 310027, China · Institute of Artificial Intelligence (TeleAI), China Telecom.

Sep 24, 2026J/K move · Enter open · S save

Echo in the Steps: Learning Perceptive Humanoid Parkour with Gated Memory

Ming-Ju Lee, Zizhuo Wang, Shaoting Zhu, Haozhe Lou+2

Tsinghua University

Legged Robotics Humanoid Robot Locomotion Terrain-Aware Robot Locomotion

Open paper AskPDF arXiv

While recent advances in perceptive locomotion have enabled humanoid robots to traverse structured terrains, agile parkour in highly discontinuous environments remains an open challenge. In particular, crossing sparse footholds and narrow support regions requires precise foothold selection, effective use of visual observations, and consistent alternating foot placement during fast transitions. In this paper, we present a perceptive humanoid parkour framework that enables stable traversal across terrains with limited foothold availability using only onboard depth observations. The framework features a saliency-guided temporal perception module that combines a saliency prior with gated memory. It retains informative depth features across frames, enabling reliable foot placement from partial observations. By introducing an alternation loss, our symmetry regularization encourages alternating gait patterns and improves traversal robustness. Extensive experiments show that our method significantly improves success rate and foothold accuracy on challenging terrains in both simulation and the real world.

Abstract

Humanoid Robot Locomotion

Explore similar work

Echo in the Steps: Learning Perceptive Humanoid Parkour with Gated Memory

Perceptive Humanoid Parkour: Chaining Dynamic Human Skills via Motion Matching

PUMA: Perception-driven Unified Foothold Prior for Mobility Augmented Quadruped Parkour