# BarlowWalk: Self-supervised Representation Learning for Legged Robot Terrain-adaptive Locomotion

arXiv: https://arxiv.org/abs/2508.00939 · HTML: https://mlsanity.com/paper/2508.00939/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in RL for robot locomotion and manipulation, one of 15 directions in Deep reinforcement learning methods.
- Builds on 18 of its 30 references that are in the map.
- First posted on arXiv 31 Jul 2025.

## Placed in

- Deep reinforcement learning methods / [RL for robot locomotion and manipulation](https://mlsanity.com/deeprl/rl-for-robot-locomotion-and-manipulation/)

## Builds on (most cited first, 18 of 18)

- [Barlow Twins: Self-Supervised Learning via Redundancy Reduction](https://mlsanity.com/paper/2103.03230/) (2021)
- [Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning](https://mlsanity.com/paper/2108.10470/) (2021)
- [Real-World Humanoid Locomotion with Reinforcement Learning](https://mlsanity.com/paper/2303.03381/) (2023)
- [Expressive Whole-Body Control for Humanoid Robots](https://mlsanity.com/paper/2402.16796/) (2024)
- [Humanoid Parkour Learning](https://mlsanity.com/paper/2406.10759/) (2024)
- [WoCoCo: Learning Whole-Body Humanoid Control with Sequential Contacts](https://mlsanity.com/paper/2406.06005/) (2024)
- [Advancing Humanoid Locomotion: Mastering Challenging Terrains with Denoising World Model Learning](https://mlsanity.com/paper/2408.14472/) (2024)
- [Not Only Rewards But Also Constraints: Applications on Legged Robot Locomotion](https://mlsanity.com/paper/2308.12517/) (2023)
- [Robust and Versatile Bipedal Jumping Control through Reinforcement Learning](https://mlsanity.com/paper/2302.09450/) (2023)
- [CTS: Concurrent Teacher-Student Reinforcement Learning for Legged Locomotion](https://mlsanity.com/paper/2405.10830/) (2024)
- [FLD: Fourier Latent Dynamics for Structured Motion Representation and Learning](https://mlsanity.com/paper/2402.13820/) (2024)
- [ImitationNet: Unsupervised Human-to-Robot Motion Retargeting via Shared Latent Space](https://mlsanity.com/paper/2309.05310/) (2023)
- [Dynamic Locomotion For Passive-Ankle Biped Robots And Humanoids Using Whole-Body Locomotion Control](https://mlsanity.com/paper/1901.08100/) (2019)
- [SLR: Learning Quadruped Locomotion without Privileged Information](https://mlsanity.com/paper/2406.04835/) (2024)
- [Force-and-moment-based Model Predictive Control for Achieving Highly Dynamic Locomotion on Bipedal Robots](https://mlsanity.com/paper/2104.00065/) (2021)
- [CDM-MPC: An Integrated Dynamic Planning and Control Framework for Bipedal Robots Jumping](https://mlsanity.com/paper/2405.11773/) (2024)
- [Bi-Level Motion Imitation for Humanoid Robots](https://mlsanity.com/paper/2410.01968/) (2024)
- [Parallel and Proximal Constrained Linear-Quadratic Methods for Real-Time Nonlinear MPC](https://mlsanity.com/paper/2405.09197/) (2024)

## Built on by (most cited first, 1 of 1)

- [Constraint-Aware Diffusion Priors for High-Fidelity and Versatile Quadruped Locomotion](https://mlsanity.com/paper/2605.08804/) (2026)

## Abstract (arXiv)

Reinforcement learning (RL), driven by data-driven methods, has become an effective solution for robot leg motion control problems. However, the mainstream RL methods for bipedal robot terrain traversal, such as teacher-student policy knowledge distillation, suffer from long training times, which limit development efficiency. To address this issue, this paper proposes BarlowWalk, an improved Proximal Policy Optimization (PPO) method integrated with self-supervised representation learning. This method employs the Barlow Twins algorithm to construct a decoupled latent space, mapping historical observation sequences into low-dimensional representations and implementing self-supervision. Meanwhile, the actor requires only proprioceptive information to achieve self-supervised learning over continuous time steps, significantly reducing the dependence on external terrain perception. Simulation experiments demonstrate that this method has significant advantages in complex terrain scenarios. To enhance the credibility of the evaluation, this study compares BarlowWalk with advanced algorithms through comparative tests, and the experimental results verify the effectiveness of the proposed method.