Data to 7 Oct 2026

Blind Bipedal Stair Traversal via Sim-to-Real Reinforcement Learning

arXiv 2105.08328 ↗First posted 18 May 2021cs.ROcited by 73

Not on the map. Why?

Abstract (arXiv)

Accurate and precise terrain estimation is a difficult problem for robot locomotion in real-world environments. Thus, it is useful to have systems that do not depend on accurate estimation to the point of fragility. In this paper, we explore the limits of such an approach by investigating the problem of traversing stair-like terrain without any external perception or terrain models on a bipedal robot. For such blind bipedal platforms, the problem appears difficult (even for humans) due to the surprise elevation changes. Our main contribution is to show that sim-to-real reinforcement learning (RL) can achieve robust locomotion over stair-like terrain on the bipedal robot Cassie using only proprioceptive feedback. Importantly, this only requires modifying an existing flat-terrain training RL framework to include stair-like terrain randomization, without any changes in reward function. To our knowledge, this is the first controller for a bipedal, human-scale robot capable of reliably traversing a variety of real-world stairs and other stair-like disturbances using only proprioception.

Key facts. Cited by 73 papers in the map (data through 7 Oct 2026). First posted on arXiv 18 May 2021.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 7; 2022: 13; 2023: 14; 2024: 21; 2025: 13; 2026: 5.

73 papers.

Sort:

By area:

2021Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learningcited by 395
2022DayDreamer: World Models for Physical Robot Learningcited by 372
2024HumanPlus: Humanoid Shadowing and Imitation from Humanscited by 164
2024Deep Reinforcement Learning for Robotics: A Survey of Real-World Successescited by 153
2024Open-TeleVision: Teleoperation with Immersive Active Visual Feedbackcited by 137
2023Real-World Humanoid Locomotion with Reinforcement Learningcited by 132
2022Rapid Locomotion via Reinforcement Learningcited by 130
2024Expressive Whole-Body Control for Humanoid Robotscited by 117
2023Robot Parkour Learningcited by 115
2024Learning Human-to-Humanoid Real-Time Whole-Body Teleoperationcited by 112
2023Learning Agile Soccer Skills for a Bipedal Robot with Deep Reinforcement Learningcited by 111
2024ExBody2: Advanced Expressive Humanoid Whole-Body Controlcited by 75

38 more

2024Reinforcement Learning for Versatile, Dynamic, and Robust Bipedal Locomotion Controlcited by 63
2022Concurrent Training of a Control Policy and a State Estimator for Dynamic and Robust Legged Locomotioncited by 61
2021Robot Learning from Randomized Simulations: A Reviewcited by 56
2024TRANSIC: Sim-to-Real Policy Transfer by Learning from Online Correctioncited by 50
2025AMO: Adaptive Motion Optimization for Hyper-Dexterous Humanoid Whole-Body Controlcited by 47
2022NeRF2Real: Sim2real Transfer of Vision-guided Bipedal Motion Skills using Neural Radiance Fieldscited by 41
2024Mobile-TeleVision: Predictive Motion Priors for Humanoid Whole-Body Controlcited by 41
2021Learning to Jump from Pixelscited by 39
2022Adapting Rapid Motor Adaptation for Bipedal Robotscited by 39
2022Advanced Skills by Learning Locomotion and Local Navigation End-to-Endcited by 39
2024Advancing Humanoid Locomotion: Mastering Challenging Terrains with Denoising World Model Learningcited by 38
2024One Policy to Run Them All: an End-to-end Learning Approach to Multi-Embodiment Locomotioncited by 34
2023DribbleBot: Dynamic Legged Manipulation in the Wildcited by 33
2022Imitate and Repurpose: Learning Reusable Robot Movement Skills From Human and Animal Behaviorscited by 27
2023Decision S4: Efficient Sequence-Based RL via State Spaces Layerscited by 26
2025Being-0: A Humanoid Robotic Agent with Vision-Language Models and Modular Skillscited by 21
2024Learning Humanoid Locomotion over Challenging Terraincited by 20
2022GoSafeOpt: Scalable Safe Exploration for Global Optimization of Dynamical Systemscited by 17
2021Model-free Reinforcement Learning for Robust Locomotion using Demonstrations from Trajectory Optimizationcited by 16
2023ManyQuadrupeds: Learning a Single Locomotion Policy for Diverse Quadruped Robotscited by 15
2024Learning Robot Soccer from Egocentric Vision with Deep Reinforcement Learningcited by 14
2025Design and Control of a Bipedal Robotic Charactercited by 12
2025Towards Embodiment Scaling Laws in Robot Locomotioncited by 12
2026Hiking in the Wild: A Scalable Perceptive Parkour Framework for Humanoidscited by 11
2024SoloParkour: Constrained Reinforcement Learning for Visual Locomotion from Privileged Experiencecited by 10
2024Stage-Wise Reward Shaping for Acrobatic Robots: A Constrained Multi-Objective Reinforcement Learning Approachcited by 10
2025Learning Humanoid Locomotion with World Model Reconstructioncited by 10
2024Rethinking Robustness Assessment: Adversarial Attacks on Learning-based Quadrupedal Locomotion Controllerscited by 9
2022Neural Scene Representation for Locomotion on Structured Terraincited by 8
2023Learning Bipedal Walking for Humanoids with Current Feedbackcited by 8
2022Learning Low-Frequency Motion Control for Robust and Dynamic Robot Locomotioncited by 7
2023Learning Robust, Agile, Natural Legged Locomotion Skills in the Wildcited by 7
2023Benchmarking Potential Based Rewards for Learning Humanoid Locomotioncited by 7
2022Learning Bipedal Walking On Planned Footsteps For Humanoid Robotscited by 5
2023Puppeteer and Marionette: Learning Anticipatory Quadrupedal Locomotion Based on Interactions of a Central Pattern Generator and Supraspinal Drivecited by 5
2023Infer and Adapt: Bipedal Locomotion Reward Learning from Demonstrations via Inverse Reinforcement Learningcited by 5
2021Learning Coordinated Terrain-Adaptive Locomotion by Imitating a Centroidal Dynamics Plannercited by 4
2022Leveraging Reward Gradients For Reinforcement Learning in Differentiable Physics Simulationscited by 4

50 most cited of 73 All 73 (JSON)