# Planning in Learned Latent Action Spaces for Generalizable Legged Locomotion

arXiv: https://arxiv.org/abs/2008.11867 · HTML: https://mlsanity.com/paper/2008.11867/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Aug 2020.

## Built on by (most cited first, 12 of 12)

- [Coupling Vision and Proprioception for Navigation of Legged Robots](https://mlsanity.com/paper/2112.02094/) (2021)
- [Hierarchical Planning with Latent World Models](https://mlsanity.com/paper/2604.03208/) (2026)
- [Hierarchical Skills for Efficient Exploration](https://mlsanity.com/paper/2110.10809/) (2021)
- [GLiDE: Generalizable Quadrupedal Locomotion in Diverse Environments with a Centroidal Model](https://mlsanity.com/paper/2104.09771/) (2021)
- [Generalized Animal Imitator: Agile Locomotion with Versatile Motion Prior](https://mlsanity.com/paper/2310.01408/) (2023)
- [Gaitor: Learning a Unified Representation Across Gaits for Real-World Quadruped Locomotion](https://mlsanity.com/paper/2405.19452/) (2024)
- [Online Damage Recovery for Physical Robots with Hierarchical Quality-Diversity](https://mlsanity.com/paper/2210.09918/) (2022)
- [Reinforcement Learning Within the Classical Robotics Stack: A Case Study in Robot Soccer](https://mlsanity.com/paper/2412.09417/) (2024)
- [Hierarchical Quality-Diversity for Online Damage Recovery](https://mlsanity.com/paper/2204.05726/) (2022)
- [VAE-Loco: Versatile Quadruped Locomotion by Learning a Disentangled Gait Representation](https://mlsanity.com/paper/2205.01179/) (2022)
- [Unifying Object-Centric World Models and Diffusion Policy: A Hierarchical Framework for Multi-Stage Robotic Tasks](https://mlsanity.com/paper/2606.08775/) (2026)
- [H-JEPA: End-to-End Learning of Hierarchical World Models for Visual Planning](https://mlsanity.com/paper/2610.06805/) (2026)

## Abstract (arXiv)

Hierarchical learning has been successful at learning generalizable locomotion skills on walking robots in a sample-efficient manner. However, the low-dimensional "latent" action used to communicate between two layers of the hierarchy is typically user-designed. In this work, we present a fully-learned hierarchical framework, that is capable of jointly learning the low-level controller and the high-level latent action space. Once this latent space is learned, we plan over continuous latent actions in a model-predictive control fashion, using a learned high-level dynamics model. This framework generalizes to multiple robots, and we present results on a Daisy hexapod simulation, A1 quadruped simulation, and Daisy robot hardware. We compare a range of learned hierarchical approaches from literature, and show that our framework outperforms baselines on multiple tasks and two simulations. In addition to learning approaches, we also compare to inverse-kinematics (IK) acting on desired robot motion, and show that our fully-learned framework outperforms IK in adverse settings on both A1 and Daisy simulations. On hardware, we show the Daisy hexapod achieve multiple locomotion tasks, in an unstructured outdoor setting, with only 2000 hardware samples, reinforcing the robustness and sample-efficiency of our approach.