# Learning Terrain Aware Bipedal Locomotion via Reduced Dimensional Perceptual Representations

arXiv: https://arxiv.org/abs/2512.12993 · HTML: https://mlsanity.com/paper/2512.12993/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in RL for robot locomotion and manipulation, one of 15 directions in Deep reinforcement learning methods.
- Builds on 26 of its 39 references that are in the map.
- First posted on arXiv 15 Dec 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, 26 of 26)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Learning robust perceptive locomotion for quadrupedal robots in the wild](https://mlsanity.com/paper/2201.08117/) (2022)
- [ANYmal Parkour: Learning Agile Navigation for Quadrupedal Robots](https://mlsanity.com/paper/2306.14874/) (2023)
- [Sim-to-Real Learning of All Common Bipedal Gaits via Periodic Reward Composition](https://mlsanity.com/paper/2011.01387/) (2020)
- [Blind Bipedal Stair Traversal via Sim-to-Real Reinforcement Learning](https://mlsanity.com/paper/2105.08328/) (2021)
- [Advancing Humanoid Locomotion: Mastering Challenging Terrains with Denoising World Model Learning](https://mlsanity.com/paper/2408.14472/) (2024)
- [ALLSTEPS: Curriculum-driven Learning of Stepping Stone Skills](https://mlsanity.com/paper/2005.04323/) (2020)
- [Learning Humanoid Locomotion with Perceptive Internal Model](https://mlsanity.com/paper/2411.14386/) (2024)
- [Feedback Control For Cassie With Deep Reinforcement Learning](https://mlsanity.com/paper/1803.05580/) (2018)
- [Learning Vision-Based Bipedal Locomotion for Challenging Terrain](https://mlsanity.com/paper/2309.14594/) (2023)
- [Attention-Based Map Encoding for Learning Generalized Legged Locomotion](https://mlsanity.com/paper/2506.09588/) (2025)
- [Parkour in the Wild: Learning a General and Extensible Agile Locomotion Policy Using Multi-expert Distillation and RL Fine-tuning](https://mlsanity.com/paper/2505.11164/) (2025)
- [CTS: Concurrent Teacher-Student Reinforcement Learning for Legged Locomotion](https://mlsanity.com/paper/2405.10830/) (2024)
- [Robust Feedback Motion Policy Design Using Reinforcement Learning on a 3D Digit Bipedal Robot](https://mlsanity.com/paper/2103.15309/) (2021)
- [Learning Bipedal Walking On Planned Footsteps For Humanoid Robots](https://mlsanity.com/paper/2207.12644/) (2022)
- [Distillation-PPO: A Novel Two-Stage Reinforcement Learning Framework for Humanoid Robot Perceptive Locomotion](https://mlsanity.com/paper/2503.08299/) (2025)
- [Template Model Inspired Task Space Learning for Robust Bipedal Locomotion](https://mlsanity.com/paper/2309.15442/) (2023)
- [Integrated Task and Motion Planning for Safe Legged Navigation in Partially Observable Environments](https://mlsanity.com/paper/2110.12097/) (2021)
- [Zero Dynamics, Pendulum Models, and Angular Momentum in Feedback Control of Bipedal Locomotion](https://mlsanity.com/paper/2105.08170/) (2021)
- [Learning Perceptual Locomotion on Uneven Terrains using Sparse Visual Observations](https://mlsanity.com/paper/2109.14026/) (2021)
- [Safe Whole-Body Task Space Control for Humanoid Robots](https://mlsanity.com/paper/2311.08409/) (2023)
- [No More Blind Spots: Learning Vision-Based Omnidirectional Bipedal Locomotion for Challenging Terrain](https://mlsanity.com/paper/2508.11929/) (2025)
- [Towards Standardized Disturbance Rejection Testing of Legged Robot Locomotion with Linear Impactor: A Preliminary Study, Observations, and Implications](https://mlsanity.com/paper/2308.14636/) (2023)
- [Data-Driven Latent Space Representation for Robust Bipedal Locomotion Learning](https://mlsanity.com/paper/2309.15740/) (2023)
- [Learning Perceptive Bipedal Locomotion over Irregular Terrain](https://mlsanity.com/paper/2304.07236/) (2023)

## Abstract (arXiv)

This work introduces a hierarchical strategy for terrain-aware bipedal locomotion that integrates reduced-dimensional perceptual representations to enhance reinforcement learning (RL)-based high-level (HL) policies for real-time gait generation. Unlike end-to-end approaches, our framework leverages latent terrain encodings via a Convolutional Variational Autoencoder (CNN-VAE) alongside reduced-order robot dynamics, optimizing the locomotion decision process with a compact state. We systematically analyze the impact of latent space dimensionality on learning efficiency and policy robustness. Additionally, we extend our method to be history-aware, incorporating sequences of recent terrain observations into the latent representation to improve robustness. To address real-world feasibility, we introduce a distillation method to learn the latent representation directly from depth camera images and provide preliminary hardware validation by comparing simulated and real sensor data. We further validate our framework using the high-fidelity Agility Robotics (AR) simulator, incorporating realistic sensor noise, state estimation, and actuator dynamics. The results confirm the robustness and adaptability of our method, underscoring its potential for hardware deployment.