The reviewed record of science sign in
Pith

arxiv: 2105.08328 · v1 · pith:4ZALN57C · submitted 2021-05-18 · cs.RO

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

Reviewed by Pithpith:4ZALN57Copen to challenge →

classification cs.RO
keywords bipedalterrainrobotstair-likeonlyproblemaccurateblind
0
0 comments X
read the original abstract

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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. GS-Playground: A High-Throughput Photorealistic Simulator for Vision-Informed Robot Learning

    cs.RO 2026-04 unverdicted novelty 6.0

    GS-Playground delivers a high-throughput photorealistic simulator for vision-informed robot learning via parallel physics integrated with batch 3D Gaussian Splatting at 10^4 FPS and an automated Real2Sim workflow for ...

  2. MoRI: Mixture of RL and IL Experts for Long-Horizon Manipulation Tasks

    cs.RO 2026-04 unverdicted novelty 6.0

    MoRI dynamically mixes RL and IL experts with variance-based switching and IL regularization to reach 97.5% success in four real-world robotic tasks while cutting human intervention by 85.8%.

  3. Iteratively Learning Muscle Memory for Legged Robots to Master Adaptive and High Precision Locomotion

    cs.RO 2025-07 unverdicted novelty 6.0

    Integrates iterative learning control with a torque library to enable high-precision adaptive locomotion on bipedal and quadrupedal robots, reducing tracking errors by up to 85% and achieving over 30x faster control rates.

  4. RANDPOL: Parameter-Efficient End-to-End Quadruped Locomotion via Randomized Policy Learning

    cs.LG 2025-05 unverdicted novelty 6.0

    RANDPOL achieves effective quadruped locomotion by training only the final linear readout of a randomly initialized and fixed neural network policy, matching PPO results with reduced parameters and enabling zero-shot ...

  5. CoRe-MoE: Contrastive Reweighted Mixture of Experts for Multi-Terrain Humanoid Locomotion with Gait Adaptation

    cs.RO 2026-06 unverdicted novelty 5.0

    CoRe-MoE uses a two-stage RL framework with contrastive reweighting in a Mixture-of-Experts architecture to enable gait transitions and multi-terrain adaptation for humanoid locomotion.

  6. SWIM: Single-Instance Whole-Body Imitation for swiMming

    cs.GR 2026-05 unverdicted novelty 5.0

    SWIM is a single-instance imitation method for learning and generalizing physically simulated swimming motions to new environments, bodies, and styles.

  7. MuGen: Multi-Skill Generative Locomotion Controller for Humanoid Robots

    cs.RO 2026-05 unverdicted novelty 5.0

    MuGen learns a generative latent representation of multi-skill humanoid locomotion from heterogeneous human data using VQ-VAEs and RL, then distills a deployable policy that tracks unseen motions and reuses the latent space.