StairMaster: Learning to Conquer Risky Hollow Stairs for Agile Quadrupedal Robots

• URL: http://arxiv.org/abs/2606.25765v1
• Date: Wed, 24 Jun 2026 12:42:06 GMT
• Title: StairMaster: Learning to Conquer Risky Hollow Stairs for Agile Quadrupedal Robots
• Abstract summary: StairMaster is a novel three-stage reinforcement learning framework for stable discontinuous on such extreme terrains.<n>To the best of our knowledge, this is the first RL-based policy to achieve steep hollow stair climbing in real-world environments.
• Score: 19.76740501133231
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Climbing hollow stairs remains a challenging problem for quadruped robots due to the high risk of leg trapping, severe depth sparsity, and high-frequency depth-sensing noise. In this paper, we propose StairMaster, a novel three-stage reinforcement learning framework for stable locomotion on such extreme discontinuous terrains. Our architecture integrates a Cross-Attention mechanism to extract structural features from noisy depth data, alongside a Spatial-aware Recurrent Unit (SRU) that maintains robust spatio-temporal memory to mitigate perception blind spots. To bridge the sim-to-real gap in depth perception, we propose a high-fidelity sim-to-real depth sensor modeling pipeline that faithfully replicates real-world sensor artifacts. Additionally, we employ a 3D waypoint-guided active perception reward for proactive sensing, alongside hollow gap kinematic and stair edge penalties to ensure precise foothold placement. We successfully deployed StairMaster on a Unitree Go2 robot, demonstrating its ability to conquer hollow stairs with an unprecedented incline of up to 55$^\circ$ through zero-shot transfer. To the best of our knowledge, this is the first RL-based policy to achieve such steep hollow stair climbing in real-world environments. Project Website: https://sivan666666.github.io/StairMaster/.

Related papers

• LadderMan: Learning Humanoid Perceptive Ladder Climbing [56.550077812088404]
  We present textbfLadderMan, a unified system that enables humanoid robots to robustly climb diverse ladders.<n>Our climbing policy is built on a scalable two-stage learning pipeline, where we use hybrid motion tracking to learn multiple climbing experts.<n>We further train a separate manipulation policy using a dual-agent formulation, allowing stable on-ladder manipulation via teleoperation.
  arXiv  Detail & Related papers  (2026-06-04T08:47:08Z)
• Explicit Stair Geometry Conditioning for Robust Humanoid Locomotion [15.718523500563203]
  This paper proposes an explicit stair geometry conditioning framework for robust humanoid stair climbing.<n>Instead of encoding terrain as high-dimensional latent features, we extract a compact set of interpretable geometric parameters, including step height, step depth, and current yaw angle relative to the robot heading.<n>These explicit stair parameters directly condition a Proximal Policy Optimization (PPO)-based locomotion policy, enabling proactive modulation of swing-foot clearance and stride characteristics according to stair structure.
  arXiv  Detail & Related papers  (2026-05-11T03:47:24Z)
• Training and Simulation of Quadrupedal Robot in Adaptive Stair Climbing for Indoor Firefighting: An End-to-End Reinforcement Learning Approach [4.901516178319544]
  Quadruped robots are used for primary searches during the early stages of indoor fires.<n> situational awareness in complex indoor environments and rapid stair climbing across different staircases remain the main challenges.<n>This project explores how to balance navigation and locomotion and how end-to-end RL methods can enable quadrupeds to adapt to different stair shapes.
  arXiv  Detail & Related papers  (2026-02-03T04:23:50Z)
• RPL: Learning Robust Humanoid Perceptive Locomotion on Challenging Terrains [53.674116167774095]
  We propose a two-stage training framework that enables multi-directional locomotion on challenging terrains.<n>RPL first trains expert policies with privileged height map observations to master decoupled locomotion and manipulation skills.<n>We then distill them into a transformer policy that leverages multiple depth cameras to cover a wide range of views.<n>For scalable depth distillation, we develop an efficient multi-depth system that ray-casts against both dynamic robot meshes and static terrain meshes.
  arXiv  Detail & Related papers  (2026-02-03T02:17:08Z)
• Gait-Adaptive Perceptive Humanoid Locomotion with Real-Time Under-Base Terrain Reconstruction [86.53248703859718]
  We introduce a perceptive locomotion framework that merges terrain sensing, gait regulation, and whole-body control into a single reinforcement learning policy.<n>Experiments conducted on a 31-DoF, 1.65 m humanoid robot demonstrate robust locomotion in both simulation and real-world settings.
  arXiv  Detail & Related papers  (2025-12-08T11:42:41Z)
• StairNetV3: Depth-aware Stair Modeling using Deep Learning [6.145334325463317]
  Vision-based stair perception can help autonomous mobile robots deal with the challenge of climbing stairs. Current monocular vision methods are difficult to model stairs accurately without depth information. This paper proposes a depth-aware stair modeling method for monocular vision.
  arXiv  Detail & Related papers  (2023-08-13T08:11:40Z)
• Legged Locomotion in Challenging Terrains using Egocentric Vision [70.37554680771322]
  We present the first end-to-end locomotion system capable of traversing stairs, curbs, stepping stones, and gaps. We show this result on a medium-sized quadruped robot using a single front-facing depth camera.
  arXiv  Detail & Related papers  (2022-11-14T18:59:58Z)
• Neural Scene Representation for Locomotion on Structured Terrain [56.48607865960868]
  We propose a learning-based method to reconstruct the local terrain for a mobile robot traversing urban environments. Using a stream of depth measurements from the onboard cameras and the robot's trajectory, the estimates the topography in the robot's vicinity. We propose a 3D reconstruction model that faithfully reconstructs the scene, despite the noisy measurements and large amounts of missing data coming from the blind spots of the camera arrangement.
  arXiv  Detail & Related papers  (2022-06-16T10:45:17Z)
• Deep Leaning-Based Ultra-Fast Stair Detection [6.362951673024623]
  We propose an end-to-end method for stair line detection based on deep learning. In experiments, our method can achieve high performance in terms of both speed and accuracy. A lightweight version can even achieve 300+ frames per second with the same resolution.
  arXiv  Detail & Related papers  (2022-01-14T02:05:01Z)
• Coupling Vision and Proprioception for Navigation of Legged Robots [65.59559699815512]
  We exploit the complementary strengths of vision and proprioception to achieve point goal navigation in a legged robot. We show superior performance compared to wheeled robot (LoCoBot) baselines. We also show the real-world deployment of our system on a quadruped robot with onboard sensors and compute.
  arXiv  Detail & Related papers  (2021-12-03T18:59:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.