# Learning Agile Locomotion on Risky Terrains

arXiv: https://arxiv.org/abs/2311.10484 · HTML: https://mlsanity.com/paper/2311.10484/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Nov 2023.

## Built on by (most cited first, 21 of 21)

- [Agile But Safe: Learning Collision-Free High-Speed Legged Locomotion](https://mlsanity.com/paper/2401.17583/) (2024)
- [RSL-RL: A Learning Library for Robotics Research](https://mlsanity.com/paper/2509.10771/) (2025)
- [BeamDojo: Learning Agile Humanoid Locomotion on Sparse Footholds](https://mlsanity.com/paper/2502.10363/) (2025)
- [PARC: Physics-based Augmentation with Reinforcement Learning for Character Controllers](https://mlsanity.com/paper/2505.04002/) (2025)
- [Stage-Wise Reward Shaping for Acrobatic Robots: A Constrained Multi-Objective Reinforcement Learning Approach](https://mlsanity.com/paper/2409.15755/) (2024)
- [Hiking in the Wild: A Scalable Perceptive Parkour Framework for Humanoids](https://mlsanity.com/paper/2601.07718/) (2026)
- [Identifying Terrain Physical Parameters from Vision -- Towards Physical-Parameter-Aware Locomotion and Navigation](https://mlsanity.com/paper/2408.16567/) (2024)
- [One Filter to Deploy Them All: Robust Safety for Quadrupedal Navigation in Unknown Environments](https://mlsanity.com/paper/2412.09989/) (2024)
- [Gait in Eight: Efficient On-Robot Learning for Omnidirectional Quadruped Locomotion](https://mlsanity.com/paper/2503.08375/) (2025)
- [Robust Robot Walker: Learning Agile Locomotion over Tiny Traps](https://mlsanity.com/paper/2409.07409/) (2024)
- [Deep Whole-body Parkour](https://mlsanity.com/paper/2601.07701/) (2026)
- [MARG: MAstering Risky Gap Terrains for Legged Robots with Elevation Mapping](https://mlsanity.com/paper/2509.20036/) (2025)
- [Mastering Diverse, Unknown, and Cluttered Tracks for Robust Vision-Based Drone Racing](https://mlsanity.com/paper/2512.09571/) (2025)
- [TOP-Nav: Legged Navigation Integrating Terrain, Obstacle and Proprioception Estimation](https://mlsanity.com/paper/2404.15256/) (2024)
- [Robust Localization, Mapping, and Navigation for Quadruped Robots](https://mlsanity.com/paper/2505.02272/) (2025)
- [A Comprehensive Survey on Physical Risk Control in the Era of Foundation Model-enabled Robotics](https://mlsanity.com/paper/2505.12583/) (2025)
- [Toward Reliable Sim-to-Real Predictability for MoE-based Robust Quadrupedal Locomotion](https://mlsanity.com/paper/2602.00678/) (2026)
- [Global-Local Attention Decomposition for Terrain Encoding in Humanoid Perceptive Locomotion](https://mlsanity.com/paper/2606.00637/) (2026)
- [Mind Your Steps: A General Learning Framework for Accurate Humanoid Foothold Tracking](https://mlsanity.com/paper/2606.08253/) (2026)
- [GeCCo -- a Generalist Contact-Conditioned Policy for Loco-Manipulation Skills on Legged Robots](https://mlsanity.com/paper/2509.17582/) (2025)
- [Spatiotemporal Agility: Time-Constrained Reinforcement Learning for Vision-Guided Dynamic Quadrupedal Interception](https://mlsanity.com/paper/2608.06907/) (2026)

## Abstract (arXiv)

Quadruped robots have shown remarkable mobility on various terrains through reinforcement learning. Yet, in the presence of sparse footholds and risky terrains such as stepping stones and balance beams, which require precise foot placement to avoid falls, model-based approaches are often used. In this paper, we show that end-to-end reinforcement learning can also enable the robot to traverse risky terrains with dynamic motions. To this end, our approach involves training a generalist policy for agile locomotion on disorderly and sparse stepping stones before transferring its reusable knowledge to various more challenging terrains by finetuning specialist policies from it. Given that the robot needs to rapidly adapt its velocity on these terrains, we formulate the task as a navigation task instead of the commonly used velocity tracking which constrains the robot's behavior and propose an exploration strategy to overcome sparse rewards and achieve high robustness. We validate our proposed method through simulation and real-world experiments on an ANYmal-D robot achieving peak forward velocity of >= 2.5 m/s on sparse stepping stones and narrow balance beams. Video: youtu.be/Z5X0J8OH6z4