# Two-Stage Learning of Highly Dynamic Motions with Rigid and Articulated Soft Quadrupeds

arXiv: https://arxiv.org/abs/2309.09682 · HTML: https://mlsanity.com/paper/2309.09682/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Sep 2023.

## Built on by (most cited first, 7 of 7)

- [DiffuseLoco: Real-Time Legged Locomotion Control with Diffusion from Offline Datasets](https://mlsanity.com/paper/2404.19264/) (2024)
- [Curriculum-Based Reinforcement Learning for Quadrupedal Jumping: A Reference-free Design](https://mlsanity.com/paper/2401.16337/) (2024)
- [PA-LOCO: Learning Perturbation-Adaptive Locomotion for Quadruped Robots](https://mlsanity.com/paper/2407.04224/) (2024)
- [Guided Reinforcement Learning for Omnidirectional 3D Jumping in Quadruped Robots](https://mlsanity.com/paper/2507.16481/) (2025)
- [Explosive Jumping with Rigid and Articulated Soft Quadrupeds via Example Guided Reinforcement Learning](https://mlsanity.com/paper/2503.16197/) (2025)
- [Learning Impact-Rich Rotational Maneuvers via Centroidal Velocity Rewards and Sim-to-Real Techniques: A One-Leg Hopper Flip Case Study](https://mlsanity.com/paper/2505.12222/) (2025)
- [SPORTS: Simultaneous Panoptic Odometry, Rendering, Tracking and Segmentation for Urban Scenes Understanding](https://mlsanity.com/paper/2510.12749/) (2025)

## Abstract (arXiv)

Controlled execution of dynamic motions in quadrupedal robots, especially those with articulated soft bodies, presents a unique set of challenges that traditional methods struggle to address efficiently. In this study, we tackle these issues by relying on a simple yet effective two-stage learning framework to generate dynamic motions for quadrupedal robots. First, a gradient-free evolution strategy is employed to discover simply represented control policies, eliminating the need for a predefined reference motion. Then, we refine these policies using deep reinforcement learning. Our approach enables the acquisition of complex motions like pronking and back-flipping, effectively from scratch. Additionally, our method simplifies the traditionally labour-intensive task of reward shaping, boosting the efficiency of the learning process. Importantly, our framework proves particularly effective for articulated soft quadrupeds, whose inherent compliance and adaptability make them ideal for dynamic tasks but also introduce unique control challenges.